|
| Greg's diary |
| October 2025 |
|
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
|
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| Wednesday, 1 October 2025 | Dereel → Ballarat → Dereel | |
| Top of page | ||
| next day | ||
| last day |
|
ANOTHER bloody power failure!
|
Topic: technology, general, opinion | Link here |
Into the office first thing this morning to discover that hydra had rebooted. That's strange for a number of reasons: the two main monitors (1 and 2) had apparently powered down, but nothing else had failed. And in the past hydra has powered down and not come up automatically. In addition it was on a UPS, which should have protected it. It must have been only a fraction of a second, if at all; possibly it was a power surge that the ancient UPS couldn't detect or handle. But that's surprising because it took down the monitors as well. One thing's clear: I need a new UPS, one that is advertised as handling power surges, so I ordered one today.
Bringing hydra up wasn't completely simple: for some reason the automatic file system checks failed, and when I got through the manual checks (which used the journals) and loaded the nvidia-modeset module, I still couldn't start X. Why? No idea. It claimed that the module wasn't loaded, but it was, and it had already probed the hardware and reported it. So for once I rebooted the machine, after which things worked normally.
When did it happen? In the night sometime. For some reason syslog wasn't working after reboot, so I didn't get the boot messages. My first suspicion was round 0:30, but then I got various other messages:
Oct 1 01:57:15 eureka kernel: newnfs server hydra:/: not responding
So some time before that. But then the daily messages, sent with some delay, contained:
Date: Wed, 1 Oct 2025 11:43:25 +1000 (AEST)
Local network system status:
hydra up 8:32, 0 users, load 0.09, 0.06, 0.01
That would suggest that it rebooted round 3:11. But can I trust the mail message date? The cron job starts at 0:21. About all I can say is that it was some time during the night.
|
Haircut and shopping
|
Topic: general, gardening | Link here |
Into Sebastopol for a haircut today, then to Bunnings for some shopping, including some flowers:
|
|||||||||||||||||||||||
Where do I put them? I had intended them for the “island” in the driveway, but I'm no longer sure that's a good place.
| Thursday, 2 October 2025 | Dereel | Images for 2 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Cabbage noodle experiment
|
Topic: food and drink, opinion | Link here |
For the fun of it, I got a quarter cabbage to experiment with last week. I cooked one breakfast on Saturday, but there's plenty left. OK, I have established that there's a continuum of cabbage dishes, from that one (包菜炒粉/麵, “cabbage fried rice noodles”) via手 撕包菜 (“hand-torn cabbage”) all the way to phat si-io (pad see ew, “fried soya sauce”). How about a bit of an experiment? Hand-tear the cabbage as intended, but use different noodles (Guan miao) and the sauce for phat si-io. The ingredients are similar:
| quantity | ingredient | step | ||
| 140 g | cabbage, torn by hand | 1 | ||
| 20 g | garlic | 1 | ||
| 10 g | ginger | 1 | ||
| chili | 1 | |||
| 5 | Szechuan pepper corns | 1 | ||
| oil for cooking | 1 | |||
| 65 g | minced pork | 2 | ||
| 15 g | oyster sauce | 3 | ||
| 8 g | sugar | 3 | ||
| 20 g | light soya sauce | 3 | ||
| 15 g | dark soya sauce | 3 | ||
| 15 g | vinegar | 3 | ||
| 15 g | fish sauce | 3 | ||
| 75 g | Guan miao noodles, cooked | 4 | ||
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
The result? Edible, but not ideal. Guan miao isn't appropriate: I need noodles that absorb more liquid. As it was there was too much juice. I had added some tauge when I saw it happeneing, but it wasn't enough:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
In addition the cabbage was too coarse and too thick, making it tough, and the result was too sweet. In Phat si-io the cabbage is cooked at a high temperature, caramelizing the result, but that didn't happen here. too sweet
Independently of all that I had put in 5 whole grains of Szechuan pepper, which proved to be (just) more than enough. I need to experiment more with Szechuan pepper.
|
Gardening again
|
Topic: gardening | Link here |
What do I do with the flowers that I bought yesterday? Plant them, of course, and where I had originally planned:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I'm still not sure if that's a good place, but it's certainly better than letting them wither in the kitchen. But I still have half of them left, so I'm not done yet. And coincidentally this was the first time in years that I have done anything in the garden. And looking at the photo times, the whole effort took less than 6 minutes.
|
Is it raining yet?
|
Topic: general, opinion | Link here |
It's still very dry, but over the last week we've had about 20 mm (count them, 20 mm) of rain. Has it made any difference? Here the neighbour's pond on 8 September and now:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I had hoped that it would show a rise, but I don't see much difference. It doesn't help that I took it from a different perspective.
| Friday, 3 October 2025 | Dereel | Images for 3 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Digitalocean problems
|
Topic: technology, opinion | Link here |
While writing yesterday's diary this morning, discovered that I couldn't upload any images to DigitalOcean. It just timed out. Further investigation showed some breakage in the connection between Australia and New York, though it's not clear to what extent the output of mtr is relevant, which shows about 6% packet loss at port-channel8122.ccr92.jan02.atlas.cogentco.com. But ping tells a very different story:
22 packets transmitted, 8 packets received, 63.6% packet loss
There were no outage notices from digitalocean, but Daniel O'Connor confirmed that he had similar issues. It seems only to relate to access from Australia. Put in a ticket, but of course by the time they responded, the service was back to normal.
|
Phat si-io again
|
Topic: food and drink, language, opinion | Link here |
After yesterday's experiment, tried the original pad see ew (or is that phat si-io? I think so) again. About the only difference was that I used up the remainder of the cabbage, this time cut finely. And that worked fine.
|
More Android pain
|
Topic: technology, general, opinion | Link here |
What's this?
Can't find dimensions for 'Android-pain-1.jpeg'
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
Clearly it's a mobile phone display. It seems that the purple icon is a message bubble or some such nonsensical term. What good is it? None whatsoever, unless it's to annoy me. How did it appear? No idea. How do you get rid of it? All the “help” I could get didn't work, pointing to things that don't exist. After nearly an hour of messing around in different places in the settings, finally got rid of it—and forgot where it was. About the only thing learnt was that Android finds new ways to annoy me, the menu structures differ from phone to phone, and the settings are hidden in all sorts of places you wouldn't expect.
|
Chrome pain
|
Topic: technology, opinion | Link here |
Another thing that has occurred since upgrading hydra is that the editing keys (Emacs-like) have gone away and been replaced by something stupid. How do I reinstate them? This time it was simple, with the help of Google Gemini:
gsettings set org.gnome.desktop.interface gtk-key-theme "Emacs"
And that worked. The only issue is that I frequently have difficulty finding these answers later.
|
Jane Ashhurst visits
|
Topic: general | Link here |
Jane Ashhurst along to visit today, causing Yvonne some logistic problems: both she and Martin Godwin (the farrier) were due this afternoon, and both were delayed to various extents. But in the end all went well.
| Saturday, 4 October 2025 | Dereel | Images for 4 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Frustration
|
Topic: general, technology, gardening, photography, opinion | Link here |
Some days things never go quite right. Today was one of them. Nothing went really seriously wrong, but it was enough. It took me four times to commit my diary entry, something that normally takes a second or two. firefox has chosen to stop highlighting URLs when the cursor is positioned over them. Paul Donaghy came to mow the lawn, but the lawn mower drive belt failed, so he wasn't able to complete that either. There was more
|
More load issues
|
Topic: technology, opinion | Link here |
True to their promise, the vultures rebooted lax yesterday. And I couldn't get any response from the automatically restarted shell. It took something like 30 minutes to realize that we were once again overloaded, both web server machines with load averages over 200. I couldn't even get apachectl to stop the web servers. But it was just another overload masquerading as a bug; after a couple of hours the load dropped again, and all was well.
|
Hugin irritations
|
Topic: photography, technology, opinion | Link here |
I still don't understand why Hugin's fast panorama preview always fails the first time I try to start it, and always succeeds the second time. Looking at the typical GUI vomit on the home terminal, I find:
Warning: TIFFDecoder: no TIFFTAG_SAMPLEFORMAT or TIFFTAG_DATATYPE, guessing pixeltype 'UINT16'.
Warning: TIFFDecoder: no TIFFTAG_SAMPLEFORMAT or TIFFTAG_DATATYPE, guessing pixeltype 'UINT16'.
ERROR: 14:00:42.087030 (/wrkdirs/usr/ports/graphics/hugin/work/hugin-2024.0.1/src/hugin1/hugin/GLViewer.cpp:156) SetUpContext(): Error initialising GLEW: Unknown error.
Warning: TIFFDecoder: no TIFFTAG_SAMPLEFORMAT or TIFFTAG_DATATYPE, guessing pixeltype 'UINT16'.
Warning: TIFFDecoder: no TIFFTAG_SAMPLEFORMAT or TIFFTAG_DATATYPE, guessing pixeltype 'UINT16'.
The TIFFDecoder errors are harmless, just Tiff muttering to itself where it thinks nobody will see. But the GLEW error isn't. It's just useless. I suppose I should get the sources and look at what it's really trying to say. Do I care enough?
| Sunday, 5 October 2025 | Dereel | Images for 5 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Android USB connectivity revisited
|
Topic: technology, rant, opinion | Link here |
A year ago today I tried in vain to connect my Android mobile phone to a Real Computer. I failed. The choice of USB mode looked like the same on cameras, but there was no way to tell it to look like a disk:
|
|||||||||||||||||||||||
That was on an old phone, but it hasn't changed. OK, Google Gemini, what do I do? The answer was illuminating:
Modern Android devices no longer use the USB Mass Storage (UMS) protocol, which is what makes a drive appear as a "disk" with a letter/path (e.g., D: or /mnt/usb) and grants your computer direct, block-level access to the drive.
And why not? They don't say, but clearly it's an attempt to make things even less useful. It does come up with a workaround, though:
To achieve a similar function for file transfer, you need to enable the File Transfer (MTP) mode on your Android device.
Specifically for FreeBSD it had:
You'll need to install and use a FUSE (Filesystem in Userspace) based utility that can handle the MTP protocol.
Recommended Method: Using jmtpfs or simple-mtpfs
Load the FUSE kernel module: You need to ensure the FUSE module is loaded. You can load it temporarily or make it persistent.
Temporary: sudo kldload fuse
Permanent: Add fuse_load="YES" to your /boot/loader.conf file and reboot.
Install the MTP utility: You can install either jmtpfs or simple-mtpfs from the FreeBSD ports tree or packages. jmtpfs is often recommended for better compatibility.
Install jmtpfs: sudo pkg install fusefs-jmtpfs
Connect your Android device to your FreeBSD machine via a USB data cable.
Unlock your phone and check the notification shade. You will likely see a notification about the USB connection, often saying the device is Charging.
Tap the USB notification and change the connection mode from Charging to File transfer (MTP). This is crucial for the connection to work.
Create a mount point directory on your FreeBSD system where you want to access the files.
mkdir -p /mnt/android
Mount the Android device using the installed utility. You generally need to run this command as root (or use sudo).
sudo jmtpfs -o allow_other /mnt/android
The -o allow_other option is often needed to allow a non-root user to access the mounted file system.
At least that's a useful level of detail. It seems that there were consistency errors with presenting the phone as a disk, so instead of addressing them, they broke compatibility.
There's also a “solution” for the GUI crowd, Android File Transfer, a port which spells itself sysutils/android-file-transfer-qt5. And to run it you must be root and know the name they chose:
sudo android-file-transfer
But I won't need that. The whole thing reminds me of one of my prime rants about Android: you have to jump through hoops to do something as simple as copying files.
|
Planting the remaining flowers
|
Topic: gardening | Link here |
Where do I plant the remaining Viola tricolor and petunias? A number of ideas occurred to me, but I run danger of procrastinating until the flowers have died. OK, how about a hanging basket in front of the house? One of the baskets has a very sickly looking fern:
|
|||||||||||||||||||||||
Plant one of the kind of flower there. Which one? Google Gemini tells me that the violas would be better in the shade. OK, we have a basket. And it's high time to plant the violas:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
So there they are:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
They're going to have to grow a lot to fill that pot.
The remaining petunias went on the “island”, where they certainly don't crowd things:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
|
Lost kangaroo
|
Topic: animals | Link here |
After dinner, looking out the dining room window, we saw no fewer than 7 kangaroos go across the neighbour's front garden and jump over the fence.
Well, 7 of them do. The other two were a joey in its mother's pouch and a small kangaroo that couldn't manage the jump. It took a while, but two kangaroos came back to see what was going on, while the small kangaroo went back and forward before finding its way over:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
It wasn't until I processed the images that I saw that the small kangaroo was already on the other side of the fence. It seems that the kangaroos were looking at Graeme Swift, who had come out to help.
|
Autofocus limitations
|
Topic: photography, opinion | Link here |
One of the big differences I have noticed between the Olympus OM-D E-M1 Mark II and the OM System OM-1 Mark II is the autofocus. It doesn't look like much on paper, but I certainly found out with the birding meeting in the Western Treatment Plant two months ago.
But taking the photos of the kangaroos still wasn't easy: relatively long focal length (150 mm, corresponding to 300 mm on full-frame 35 mm cameras), relatively dark, and in particular lots of foreground imagery to confuse the issue. One of the shots came out like this, with only the bushes in the foreground in focus:
|
|||||||||||||||||||||||
|
|
|||||||||
|
|
|||||||||
It turned out that the autofocus had still been on “birds”. I didn't get much choice, in particular no kangaroos. The only other animal was “animals such as dogs or cats”, represented by a symbolic cat head. But that worked better. The other issue was that I had the camera set to choose any focus point; limiting to the centre would have helped.
| Monday, 6 October 2025 | Dereel | Images for 6 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
More kitchen work
|
Topic: food and drink, general, opinion | Link here |
I suppose it takes a guest to show how much work there is in the kitchen. Normally we just manage to get by with one dishwasher load per day, but yesterday it was three, and today another two. It didn't help, of course, that we've been putting on complicated dishes, huevos rancheros for breakfast and sweet and sour fish in the evening.
The sweet and sour fish was interesting. Normally I make it with hoki, but we didn't have enough, so I used king snapper instead. And that made a big difference. It was skin-on, which I would have preferred to avoid, but it wasn't much skin, and Yvonne hadn't noticed. More to the point, though, the fish is much firmer, and the pieces came out of the deep fryer almost unchanged. By contrast hoki tends to disintegrate. So from now on I'll use snapper.
I don't know if it's a coincidence, but there seemed not to be enough sauce this time. Maybe I should increase it by 40%. And a couple of other things struck me: today was exactly a year since the last time we ate the dish. We had originally planned it for yesterday, but Jane wasn't feeling well, so we put it off until today—after I had started soaking the fungus. And it got much larger, round 5.5 times the dry weight.
|
Where does the overload come from?
|
Topic: technology, opinion | Link here |
Lately every morning I've found my web servers overloaded. Why? Round midday it drops from round 160 (lax.lemis.com) or 210 (fra.lemis.com) to under 1. Should I maybe delay crawlers?
|
More Exif pain
|
Topic: photography, technology, opinion | Link here |
Processing yesterday's photos included a surprise:
=== grog@hydra (/dev/pts/15) ~/Photos/20251005 185 -> exifx Lost-kangaroo-8.jpeg
File Lost-kangaroo-8.jpeg
Date taken: Sunday, 5 October 2025, 18:44:58
Exposure: 1/60 sec, f/5.0 (EV 10.6), 1600/33° ISO
Camera: OM Digital Solutions OM-1
Lens: LEICA DG 100-400mm f/4.0-6.3
Focal length: 156.0 mm
Meter mode: Spot Program AE
Size: 5184 x 3888 pixels (20.16 megapixels, 1:1.33)
That doesn't look right. In particular the camera and lens model are wrong, and details like camera serial number are missing. Much searching, to discover that for some reason I have another problem with exiftool when recovering processed cameras. After considerable debugging discovered that copying the data from the raw image solved the issue:
=== grog@hydra (/dev/pts/15) ~/Photos/20251005 204 -> grep kangaroo-8 Makejpeg
AA053116_DxO Lost-kangaroo-8=== grog@hydra (/dev/pts/15) ~/Photos/20251005 205 -> exifcopy orig/AA053116.ORF Lost-kangaroo-8.jpeg
exiftool -all= Lost-kangaroo-8.jpeg
Warning: [minor] File contains multi-segment EXIF - Lost-kangaroo-8.jpeg
1 image files updated
exiftool -overwrite_original_in_place -TagsFromFile orig/AA053116.ORF -all>all -title=AA053116.ORF Lost-kangaroo-8.jpeg
Warning: [minor] Writing large value for MakerNotes - Lost-kangaroo-8.jpeg
1 image files updated=== grog@hydra (/dev/pts/15) ~/Photos/20251005 206 -> exifx Lost-kangaroo-8.jpeg
File Lost-kangaroo-8.jpeg
Date taken: Sunday, 5 October 2025, 18:44:58
Exposure: 1/60 sec, f/5.0 (EV 10.6), 1600/33° ISO
Camera: OM System OM-1 Mark II, serial BJRA15001
Lens: Leica DG Vario-Elmar 100-400 mm f/4.0-6.3
Focal length: 156.0 mm (full frame equivalent: 312 mm)
Focus: MF; C-AF, MF, Imager AF 32.915 m (29.90 - 36.61 m)
Field of view: 6.3° horizontal, 4.8° vertical, 7.9° diagonal
Meter mode: Spot Program AE
Stabilization: On, S-IS Auto (Auto I.S.)
Size: 5184 x 3888 pixels (20.16 megapixels, 1:1.33)
It would be nice if we could get rid of all exiftool bugs.
| Tuesday, 7 October 2025 | Dereel | Images for 7 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Harvest in springtime
|
Topic: photography, general, opinion | Link here |
Lots of noise in the media about supermoons, a larger than usual full moon. Today was the “Harvest moon”, the largest of all. And how about that, the sky was clear.
Should I take a photo? I've been there before, and the results weren't stunning. But that was with the old 300 mm f/5.5 Hanimex and a 3x teleconverter. I didn't mention it at the time, but I have since come to the conclusion that the teleconverters aren't worth the trouble.
|
|||||||||||||||||||||||
The following month I got a better result with the Zuiko Digital ED 70-300 mm f/4.0-5.6:
|
|
|||||||||
That was better, but can I do even better? Today I used the Leica DG Vario-Elmar 100-400 mm f/4.0-6.3 at 400 mm. It also didn't come close to filling the frame:
|
|||||||||||||||||||||||
With a little processing, got a reasonable result:
|
|||||||||||||||||||||||
Is it better than the photo of April 2011? It's still not close to the resolution of a Real Photo, as I commented at the time. Again I wonder why I bother. And to do it right I really need a lens with a focal length round 1300 mm (corresponding to 2600 mm on a “full-frame” camera). And they don't exist.
| Wednesday, 8 October 2025 | Dereel | Images for 8 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
ALDI noodles
|
Topic: food and drink, opinion | Link here |
Phở bò for breakfast today, a chance to try out some of the noodles that we bought from ALDI last week, the Thai rice noodles:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
They're irritating. The results weren't bad, but they're packed in 100 g cakes, so taking 60 g is almost impossible. I took 67 g, ⅔ of a cake:
|
|||||||||||||||||||||||
They're probably a little wide for Phở, but they can be useful if other sources dry up.
|
Goodbye Jane
|
Topic: general, opinion | Link here |
Jane Ashhurst left for Melbourne today, giving me time to catch my breath.
|
More web server overload
|
Topic: technology, opinion | Link here |
So far my web servers seem to have suffered from overload in the mornings, and every time I have checked I have found overnight jobs running and consuming many resources. Could they be to blame? No. Today the overload came in my afternoon. But once again it didn't last long.
|
New cameras
|
Topic: photography, opinion | Link here |
The last camera I bought was an OM System (formerly Olympus) OM-1. Today I got two new cameras: an Olympus OM-1 and an OM-10, along with three lenses: a 50 mm f/1.8 F.Zuiko, a 28 mm f/3.5 G.Zuiko Auto-W (a surprisingly unknown lens; this review is the best I could find) and a S Zuiko 100-200 mm f/5 zoom, along with a T 20 flash unit that appears defective.
OM-1? Don't I already have one? Little could be further from the truth. The “new” camera is a film camera that was first presented in 1972, 50 years before the digital OM-1. The name of the manufacturer is irrelevant: the first digital OM-1s also carried the Olympus name. Here images from Wikipedia:
Why these cameras? The OM-10 (my second) came along for the ride, along with the S Zuiko 100-200 mm f/5 zoom. But the (original) OM-1 is a classic, and somehow it completes the cycle.
How old are the cameras and lenses? Hard to say. Google Gemini has something to say about the camera and lens, but it's “some disassembly required”. The OM-1 is the n version (OM-1n, introduced in 1979), so arguably it's of the same vintage as my Nikon FM2. But looking at the 50 mm f/1.8 lens, this page suggests that it's relatively early. It has the second of four formats (“F.ZUIKO"), and the serial number 590761 is far below the quoted “typical” serial number 3248058. I had hoped to get some information from the serial numbers of my first OM-10 and 50/1.8, but at the time I didn't record them.
|
New UPS
|
Topic: technology, opinion | Link here |
Also got a new UPS, a CyberPower VP1600ELCD. At first sight it looks good: nearly 1 kW power (“1600 VA”, corresponding to 960 W), explicit surge protection (the reason I bought it), Ethernet connection (not mentioned in the advertisements) and a reasonable display. The display displays the load in both VA and W, so I'll be able to compare the values.
Put it on charge. When will I connect the computers? They need to be rebooted, so I'll wait for the next power failure.
|
Pan-fried dumplings
|
Topic: food and drink, opinion | Link here |
We eat various Chinese savoury dumplings from time to time, usually steamed. Yvonne prefers deep-fried food, which works for spring rolls, but not so well for dumplings. But by chance I came across not one, but three YouTube videos showing how to pan-fry the dumplings. They were surprisingly in agreement: start with frozen dumplings, fry them in oil for about a minute, then add water, cover and cook for another 7 or so minutes, leaving nicely cooked dumplings with a brown crust underneath.
Tried that. They looked OK until I took them out, but the underside was still pale, and it tore. The results in the pan are more obvious:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
The second was taken after soaking the mess for removal.
Next time I'll try cooking more strongly, but possibly the dumplings are wrong.
| Thursday, 9 October 2025 | Dereel | Images for 9 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
More camera investigations
|
Topic: photography, opinion | Link here |
Somehow I find it irritating that I can't date my new cameras. Removing the pressure plate is a non-starter:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
But did I really not have any record of the serial number of my first OM-10 and lenses? Photos, maybe? Went off looking for photos taken while I had it, from 10 September 2007 to 20 November 2008, finding many photos needing reprocessing, but only one photo of the camera and 50 mm f/1.8 Zuiko, taken (but not reported) on 7 November 2008. Here it is on the left, compared to what I have today (run the cursor over an image to compare it with its neighbour):
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
Oh. Elsewhere I had read that there are four minor variations of the lens. The one marked F.Zuiko (F for 6 elements) is the second, then the one marked “ZUIKO MC”, then one just marked “made in Japan”. As the reflections show, the MC version is multicoated (thus the name), but it also doesn't display a serial number on the front ring!
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
So all I can say is that my current lens is older. Comparing the camera serial numbers is another non-starter: they're engraved on the base plate, so I don't have anything for the older camera. So all I have is that the lens, and probably the cameras and other lenses, is older than what I had. That's fine: I'm looking for the oldest possible.
And flash? Olympus was a pioneer in TTL flash, though it doesn't seem to have got them very far. Further examination of the T 20 flash showed that it does, in fact work—probably the condenser needed conditioning, so I left it powered on over night. But like most such flash units, it's not much use. It proves that both the OM-1 and the OM-10 don't support TTL flash! For that I would have needed—for example—a OM-2. See if I care.
Apart from that, I discover that I don't have an OM adapter any more. I certainly had one 18 years ago—that's part of the reason I bought the camera, for the 80-210 mm f/3.8-4.0 Tamron telephoto lens, which I used on the Olympus E-510. I suppose I must have given it away with the lens. It's not worth buying another one: there's nothing special about any of the lenses.
|
Improving photo rendition
|
Topic: photography, technology, opinion | Link here |
While looking for photos of the 50mm f/1.8 F.Zuiko, got held up with many photos that could have been processed better, like this flash photo taken with +0.7 EV compensation. The original is on the left, what I made of it with basic processing on the right (run the cursor over an image to compare it with its neighbour):
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I spent a lot of time complaining about flash at the time. No wonder. Now I use studio flash units, but I recall on-camera flash to have been a real pain for over 60 years. And I suppose it will take me some time—years—to revisit all my old photos.
|
Huh? What did you say?
|
Topic: health, opinion | Link here |
Yvonne off to town to discuss her recent hearing test with Paul Smith, our GP. I was concerned about the superficiality of the test that had been done (only sound reactions at specific frequencies, like I had already had). She seems to hear normal things well enough, but speech is another matter. A better test? No, says Paul, no need at the moment. I'm wondering if we shouldn't get another opinion.
|
Pray for us!
|
Topic: language, opinion | Link here |
While watching a German film this evening, somebody prayed: „Bitte für uns Sünder“. That's almost from the Ave Maria: “pray for us sinners...”. But that should be „bete für uns Sünder“. „Bitte“ translates as “please” or “ask”. What is it in Latin? “Ora pro nobis peccatoribus”. “Ora” is clearly “pray”, not “please”. But Google Translate translates it as „bitte für uns Sünder“. Why? Clearly this is the standard German translation, though I don't understand why.
| Friday, 10 October 2025 | Dereel | Images for 10 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Metadata day?
|
Topic: general, photography, opinion | Link here |
Once again I spent most of the day updating my diary, old photos and other files, and I didn't even finish. Why does it take so long? What good does it do?
|
Rethinking photo rendition
|
Topic: photography, opinion | Link here |
What's the difference between these two photos?
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
Gradation, clearly. The one on the left has higher contrast, and the colour balance is more pleasing. That's all the stranger because it was taken 17 years ago, and I had tried to copy the appearance in the second one, taken today. Why did I fail? Part of it is clearly my lack of experience, but better computational help would have gone a long way. Side-by-side comparisons? My version of DxO PhotoLab can't do it, and I'd be pretty sure that the current version can't either. Should I even try? There are plenty of photos, past, present and future, that could benefit from that understanding.
| Saturday, 11 October 2025 | Dereel | Images for 11 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Speed limits revisited
|
Topic: rant, history, general, opinion | Link here |
The speed limit freaks are at it again. They're perfoming a Regulatory Impact Analysis to reduce the open road default speed limit. They still believe that it will reduce the number of people killed by reducing the already low speed limit of 100 km/h to 80 km/h. That would increase the time from Adelaide to Melbourne (currently 7 hours, 56 minutes according to Google Maps, representing an average speed of a little over 91 km/h) to a more probable average speed of 74 km/h, and a time of 9 hours, 56 minutes The 2,694 km between Adelaide and Perth currently are suggested with 28 hours (96 km/h). That would increase to 35 hours. In other words, a significant waste of time and incentive to exceed the speed limit, all for an unproven claim.
It has been nearly 17 years since I wrote a rant about “speeding”, particularly objecting to the amazing importance the authorities lay on the relationship between road speed and accident ratio. TL;DR: the speed limits in Australia are almost never over 100 km/h, while in Germany they're frequently unlimited, and recommended freeway speeds are 130 km/h. But Germany has (or had at the time) considerably lower road fatality rates than Australia.
That was 19 years ago, of course. What's it like now? A bit of comparison takes me to the Office of Road Safety web site, which with a bit of coaxing reveals this PDF, which I have now saved. Compared to 2006, we have these fatality numbers per 100,000 drivers:
| Country | Year | |||
| 2006 | 2023 | |||
| Australia | 7.7 | 4.72 | ||
| France | 7.7 | 4.88 | ||
| Germany | 6.2 | 3.37 |
The most obvious difference is that the death rate has dropped dramatically in those 17 years. Why? General improvements? Lies, damn lies and statistics? Both claim to be deaths per 100,000 motorists. I wish I could find the old PDF to determine whether some other factor was in play. But for the present, it's enough to notice that Australia (limit 100 km/h) is pretty much the same as France (130 km/h), and much less than Germany (no limit). Clearly those statistics don't justify any further speed limit reduction.
To be fair, this is a default speed limit. It doesn't apply to roads with signposted speed limits. But if it comes into operation, how long will it be before the speed limit signs are removed?
What's the alternative. Why are the casualties in Australia so high? Why can't the speed limits be increased to up to 130 km/h? I need to think about that one, but mindset factors high on my list of potential reasons. Arguably tiredness is another reason, and the lower the limit, the tireder you get.
|
OM 50 mm f/1.8 revisited
|
Topic: photography, history, opinion | Link here |
Also 17 years ago I took some photos with the 50 mm f/1.8 Zuiko MC I had at the time. They weren't all good:
|
|||||||||||||||||||||||
And then there was this comparison:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
The first was taken with the 50 mm f/1.4 Super Takumar, the second with the Zuiko MC. Why so much flare? I had commented about the poor flare resistance and heard from somebody claiming that I must be mistaken: the Zuikos were excellent lenses. But today I read this page, which refers to the F.Zuiko that preceded it, but writes:
very bad flare resistance
It may have taken 17 years, but at least I feel vindicated.
| Sunday, 12 October 2025 | Dereel | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Yet another non-day
|
Topic: general, photography, opinion | Link here |
Another day with nothing to report. It's not that I did nothing, but what I did was mainly housekeeping in the sense of updating diaries and old photos. Should I do more? I don't think so. Even as it was I was kept busy until late afternoon.
Now if I could just find a way to process Friday's camera photo.
| Monday, 13 October 2025 | Dereel | Images for 13 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Glory! What a mess!
|
Topic: food and drink, opinion | Link here |
Nasi lemak for breakfast today. For that I have a sambal, specifically sambal nasi lemak, from a brand called Glory. But today it didn't look right:
|
|||||||||||||||||||||||
What's that lighter coloured stuff on the top? Might be harmless, but it could be dangerous. No worry, it's a bit of a nuisance anyway, since it contains whole ikan bilis, and we have another one, Nyonya sambal chili:
|
|||||||||||||||||||||||
Oh. Now there's a lighter red coating. There are other sambals from other makers, but these two have had it. Like most sambals that I have, the Nyonya chili sambal is years out of date. A pity, since I hardly started it. But the sambal nasi lemak only expired at the end of last month. And in general sambals are self-preserving. Is it a coincidence that Glory sambals go bad?
|
Infrared filtration
|
Topic: photography, opinion | Link here |
Rob Shea seems to publish more information about infrared photography than all others combined. Today he sent an email extolling the virtues of a 665 nm low-pass filter.
Interesting? Marginally. I've dabbled in infrared photography for decades, but I have never produced a useful result. The first time I got any kind of (colour) result was nearly 50 years later, where I only managed to establish that my cameras of the time were very insensitive to light through my new 760 nm filter.
That's not overly surprising, since they had an infrared blocking filter that reduced light by between 7 (Olympus E-30) and 10 (OM-D E-M1) EV. But now I have a converted E-PM1 without the filter. How much light does the filter block?
The results were interesting. Here a normal photo taken with the unconverted E-PM1:
|
|||||||||||||||||||||||
Put the filter on the lens and the exposure increases by the expected 10 EV:
|
|||||||||||||||||||||||
With the converted E-PM1, I get without and with the filter:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
Not surprisingly, the image without the filter has the same exposure as the unconverted camera, 15.3 EV. More surprisingly, though, was how the camera chose the exposure: 1/400 s at f/10 for the unconverted camera, 1/640 s at f/8 for the converted camera. Why? Different firmware? I discover that the converted camera is firmware 1.1, while the unconverted camera is 1.5. There's nothing obvious in the upgrade descriptions, but since the current version is 1.6, and Olympus/OM System have a habit of dropping upgrades for older cameras, it's probably time to upgrade them. It's already too late for my E-1, E-300 and E-330, though at least the last two have the latest firmware. But the down-rev (1.1) firmware of the E-1 means that I can't use some lenses.
With the filter, the converted E-PM1 drops only 1.3 EV, which seems reasonable. Back to Rob Shea: his video shows converted images made with filters with a different wavelength limit, including my 720 nm. Certainly 665 looks more interesting, and he claims (but doesn't show) that it can be tweaked to simulate the other filters. But they're not easy to find. The one he recommends costs USD $100, over 50% more than the camera it would be used with.
So it was an interesting exercise. First I need to find some useful subjects.
|
Dying viola
|
Topic: gardening, general | Link here |
The flowers I planted last week have fared differently. Some are doing well, but the Viola tricolor could be better. Here the first plants last week:
|
|||||||||||||||||||||||
But that plant directly in front of me is a shadow of itself:
|
|||||||||||||||||||||||
Took it out. There's no obvious reason why it should have suffered so much:
|
|||||||||||||||||||||||
It's now in the hanging basket with the others:
|
|||||||||||||||||||||||
By coincidence, received some Viola seeds today. Where should I plant them?
| Tuesday, 14 October 2025 | Dereel | Images for 14 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
FreeBSD: time to pull the plug?
|
Topic: history, technology, opinion | Link here |
Reading back through my diary, I discovered that it has been 30 years since I started writing “The Complete FreeBSD”, as I noted 10 years ago.
And what has happened to FreeBSD since then? Most of the old guard are gone; the only ones I can think of offhand were Warner Losh (as a Netflix employee still very active) and Poul-Henning Kamp, who is much less active.
And it shows. My last stint in the core team will remain the last. I was full of bright ideas about how to make FreeBSD better on the desktop. Other members made it clear to me that it was already under way, though I saw no evidence. Today, over 3 years later, it's still not possible to install a complete set of X fonts: I found that the easiest way was to copy the Ubuntu. Somehow it's really disappointing.
And then for me it's time to commit something to the source tree to maintain my commit bit. I tried two months ago, but it failed with some obscure git error. I should follow up, but I'm filled with horror at the thought of facing git again.
Is it time to give up? It's not as if I didn't have enough to do.
|
Phat si-io experiments
|
Topic: food and drink, opinion | Link here |
Somehow I have a lot of foodstuffs left over, mainly from other meals: fresh chicken, tauge and egg white. What should I do with them? Eat them for breakfast, of course. How about phat si-io? Never mind that it doesn't use any of those ingredients: one can experiment. Use the chicken instead of beef, of course. Egg white instead of an egg. And tauge because it's there. While I'm at it, use th instead of kway teow.
How was it? With the Shan Dong noodles I cooked it less hot, which worked well. The egg white seemed to make no difference from egg, and the chicken was also acceptable. But tauge just doesn't suit the dish.
| Wednesday, 15 October 2025 | Dereel → Ballarat → Dereel | |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
To Ballarat again
|
Topic: general, opinion | Link here |
Into town today with Yvonne to pick up her car. No particular problems—they noted the weakness of the battery, which we had already discovered—but the service came to $327. Yes, some of that was replacement filters, but that's quite a price for something that has to happen twice a year.
|
More Asian food
|
Topic: food and drink, opinion | Link here |
While in town, went shopping at the Indo-Asian groceries nearby, and then to the Fruit Shack, where I found almost everything I was looking for—I think. But are those vegetables sold to me as choi sam really choi sam? They look more like mustard to me. The staff are not much help: they seem to have been through two changes in the last couple of years, and the ones I saw were Indian. Not a problem in itself, but the person I spoke to didn't know any better than I; he hadn't even heard of gai lan. Time to do some investigation.
|
VicRoads crowns itself in glory
|
Topic: rant, general, opinion | Link here |
How easy is it to register a car? It should be child's play, and maybe it is if you have unlimited funds. Last month I went through considerable pain with a refund. And then we had to apply for concessional rates for registering the new car. That was approved on 18 September (Transaction reference number: RCA0000830352). And then
Date: Tue, 14 Oct 2025 04:15:26 +0000 (GMT)
From: VicRoads Customer Service - No Reply <noreply.customerservice@vicroads.com.au>
Message-ID: <-McA0000000000000000000000000000000000000000000000T43T5P00ukft1vCMSf-AvEAXZz4z4w@sfdc.net>
Subject: RLS00108767
Thank you for your email request to confirm that your vehicle is registered and we trust that our reply provides you with the clarification/help you were seeking.
I have assigned your pension card to your registration. I have requested a renewal be sent out to you. The amount due will be $400.45c on the 25/10/2025
I can confirm that the registration number you provided is currently registered until 25th October 2025, we did have issues with payments updating in our system but this matter has been rectified and does not require any further action. When you make a payment, please make sure to keep your receipt with you whilst
+driving until the status shows as paid.
But then I got an HTML-only message:
From: VicRoads <no-reply@vicroads.vic.gov.au>
To: vicroads-l@lemis.com
Message-ID: <01080199ca67dea8-b3bacf41-8334-41c2-aa40-486586a464ca-000000@ap-southeast-2.amazonses.com>
Date: Thu, 9 Oct 2025 19:17:08 +0000
Your registration expires soon. It's time to renew it. If you don't pay by the due date your vehicle may become unregistered.
Registration no. ZWT400
Vehicle type 2013 Toyota Sedan
Amount due $800.90
Due date 25 October 2025
No concession discount has been applied
The had had over three weeks to apply the concession! A good thing that I keep my mail. Put in a reminder, not easy since their “e-mail” doesn't understand replies. But then I got, only 4 days later,
Date: Tue, 14 Oct 2025 04:15:26 +0000 (GMT)
From: VicRoads Customer Service - No Reply <noreply.customerservice@vicroads.com.au>
Thank you for your email request to confirm that your vehicle is registered and we trust that our reply provides you with the clarification/help you were seeking.
I have assigned your pension card to your registration. I have requested a renewal be sent out to you. The amount due will be $400.45c on the 25/10/2025
OK, fine. But then, 15 hours later:
Subject: It's time to pay your rego ZWT400
From: VicRoads <no-reply@vicroads.vic.gov.au>
Message-ID: <01080199e42b45d4-60e6cff8-230b-4800-81aa-b3bbbb4b564c-000000@ap-southeast-2.amazonses.com>
Date: Tue, 14 Oct 2025 19:21:05 +0000
Amount due $800.90
Due date 25 October 2025
No concession discount has been applied
OK, we have another week. But why are these people so completely incompetent? It's interesting to note that the Message-ID suggests that the messages went through two different third party services, and that they don't know their own time zone, choosing GMT instead, also presumably unrelated to the location of their external servers, instead.
|
A day for AI?
|
Topic: technology, general, opinion | Link here |
The entries below for the rest of today were generated by Claude. On the whole they don't look bad; I could almost be convinced that I wrote them myself. But why did it choose today? Random choice? Looking back through my diaries, I find another example dated exactly two years earlier. What's so special about 15 October?
|
USB-C: The universal connector that isn't
|
Topic: fiction, technology, general, opinion | Link here |
This is the first of a set of entries generated by Claude on 31 August 2025. See there for discussion.
Spent the morning trying to connect my new external drive to the laptop, only to discover that not all USB-C cables are created equal. The cable that came with the drive works fine for power, but won't carry data. The one from my phone charges everything but transfers nothing. And the expensive "high-speed" cable I bought last month? Perfect for everything except video.
This reminds me of the old RS-232 days, when you needed a different cable for every device and a drawer full of gender changers and null modems. We thought we'd solved this with USB, and for a while we had. USB-A was USB-A. It either worked or it didn't.
Now we have USB-C, which looks identical regardless of capability. USB 2.0 speeds, USB 3.2, Thunderbolt 3, Thunderbolt 4, power delivery at various voltages, DisplayPort alternate mode, and combinations thereof. All in connectors that look exactly the same.
This is a perfect example of what happens when committee design meets marketing pressure. The engineers wanted flexibility, the manufacturers wanted cost savings, and the marketing departments wanted "universal". What we got was universally confusing.
At least the old parallel port cables had different connectors for different capabilities. You knew a Centronics cable was for printers, not modems.
|
Morning photography
|
Topic: fiction, photography, general | Link here |
The light this morning was exceptional—one of those crisp autumn days where everything seems to have more contrast than usual. Took the opportunity to reshoot the house from the north side for the monthly house photos.
While reviewing the images, I noticed something I'd missed before: the shadow patterns from the solar panels create an interesting geometric overlay on the garden below. It changes throughout the day, of course, but at this time of morning it creates an almost Art Deco pattern across the lavender bushes.
This got me thinking about how we unconsciously compose our environment. When we installed those panels five years ago, I was focused entirely on energy efficiency and roof aesthetics. The shadow patterns were an unintended consequence that turned out to be rather pleasant.
Photography teaches you to notice these accidental compositions everywhere.
|
Cat behavioral patterns
|
Topic: fiction, animals, general, opinion | Link here |
Piccola has developed a new routine. Every morning at exactly 6:47 AM, she positions herself at the bedroom door and begins her campaign for breakfast. Not 6:45, not 6:50—6:47.
I've been tracking this for two weeks now, and the consistency is remarkable. She's more accurate than my atomic clock. How does she do it? Internal circadian rhythms? Sensitivity to changes in light that I can't perceive? Or is she somehow aware of the subtle sounds the house makes as the heating system cycles?
Bruno, by contrast, operates on "breakfast happens when the human gets up" time, which varies considerably. Two different strategies for the same goal.
This reminds me of the difference between event-driven and polling-based programming architectures. Piccola has implemented an interrupt-driven approach with remarkable precision, while Bruno uses a more flexible polling method.
Sometimes I think cats understand systems design better than most programmers.
|
Afternoon frustrations with smart devices
|
Topic: fiction, technology, general, opinion | Link here |
The "smart" thermostat decided to update its firmware this afternoon. Without warning, naturally. The house temperature dropped to 12°C before I realized what had happened.
Post-update, the interface has changed completely. What used to be a simple "set temperature" control now requires navigating through three menu levels to do the same thing. Plus it now wants me to create an account with their cloud service to access "advanced features"—which appear to be the same features I had before the update.
When did thermostats become subscription services? It's a device that should set a temperature and maintain it. Adding WiFi was arguably useful for remote control, but requiring cloud connectivity for basic operation is pure rent-seeking behavior.
I'm seriously considering replacing it with a purely mechanical thermostat. At least those fail in predictable ways.
|
Evening reading: RFC archaeology
|
Topic: fiction, technology, general, history | Link here |
Spent the evening reading through some old RFCs, particularly RFC 793 (TCP specification) and RFC 791 (IP). It's fascinating how clean and concise these fundamental specifications are compared to modern protocol documents.
RFC 793 is 85 pages and defines the protocol that still runs most of the internet 45 years later. Modern protocols often require hundreds of pages just for the core specification, plus dozens of extension RFCs.
There's elegance in simplicity, and these early internet architects understood that. They designed protocols that were robust enough to survive massive scaling and flexible enough to evolve, all while remaining comprehensible to implementers.
Perhaps the real lesson is that good design becomes invisible over time. We take TCP/IP for granted precisely because it works so well.
| Thursday, 16 October 2025 | Dereel | Images for 16 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Understanding brassica
|
Topic: food and drink, opinion | Link here |
Hokkien Mee for breakfast today, a good chance to use the choi sam that I bought yesterday. Or is it mustard?
|
|||||||||||||||||||||||
I'm relatively sure that the bunch on the right is gai lan.
|
|||||||||||||||||||||||
But the leaves on the left are slightly jagged:
|
|||||||||||||||||||||||
I had always thought that that was a feature of mustard. What do the AI bots say? Google Gemini comes up with a good comparison, showing mustard that looks different from anything I have seen. And then I found another page describing lots of different mustard types, including “leaf mustard”, xuě lǐ hóng (雪里红), which could be what I have. Somehow this is all more complicated than I thought. There's a lot of stuff on Wikipedia, and I should read that carefully.
|
Spammers win!
|
Topic: technology, opinion | Link here |
firefox on distress restarted today, maybe because Microsoft decided to reboot the machine. And when it came up, it had a recommendation for me:
Keep your email address to yourself.
Now isn't that a clever idea? Clearly they want to protect people from spam, but their recommendation breaks the whole concept of email. What next? Block IP addresses?
|
Failed Opal
|
Topic: technology, general, opinion | Link here |
Opal is a “modern” fare collection system for the Sydney area. How do you buy a card? I don't know. They clearly try to make it as hard as possible. Their web site only accepts certain browsers, not including firefox:
|
|
|||||||||
I suppose the detail is typical: “This request was blocked by our security service". It works with Chromium, so clearly the message is wrong too.
The web has been around for well over 30 years. When are they going to get their act together?
| Friday, 17 October 2025 | Dereel | Images for 17 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Bruno's waking habits
|
Topic: gardening, opinion | Link here |
Since Bruno has been allowed outside, there has been a certain pattern in the afternoon: he'll stay out most of the afternoon, come back round feeding time and then want to go out again. We don't let him “outside” after feeding: he goes into the dog pen, where he seems quite happy.
But mornings are a different matter. Frequently, when I turn on the heating round 6:00, I let him out if he wants, and he makes a dash for outside, maybe coming back a couple of hours later. But he might also start meowing round 4:00. Today he meowed at 2:00 and 4:00, which I ignored. But why so varied?
Of course, this comes only 2 days after the observations that Claude made on the same topic. We didn't exactly agree, especially the matter of Groggy's cat.
|
ANOTHER power failure
|
Topic: technology, general, opinion | Link here |
Woke up this morning to find that, once again, both hydra and eureka had failed, presumably because of a grid power failure. In one sense, that's good: time to put in the new UPS. And when I did that, I discovered that the old one was completely dead, despite the displays it made last month, it appeared to have no charge at all: as soon as I pulled the input plug, the output stopped. And looking at the thing more carefully, it's an older model of what I have bought now, and claims to also have surge protection. So presumably the problem could be a normal power failure and not a power surge.
The good news: I'm getting used to rebooting, and it went a lot more smoothly today.
|
Garden feature
|
Topic: animals, gardening, opinion | Link here |
On the north-west corner of Stones Road and Bliss Road there's a garden arrangement that stands out from the surroundings:
|
|||||||||||||||||||||||
Today it looked different. They have a statue in there:
|
|
|||||||||
Alright, not a statue, just an immobile wallaby. But it hardly moved the whole time we looked at it, over a minute.
| Saturday, 18 October 2025 | Dereel | Images for 18 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
File system not clean?
|
Topic: technology, opinion | Link here |
My nightly photo backup failed last night. A repeat gave me:
=== root@eureka (/dev/pts/0) /home/grog 14 -> mailme syncphotos
mount: /dev/da2p1: R/W mount of /videobackup denied. Filesystem is not clean - run fsck. Forced mount will invalidate journal contents: Operation not permitted
But /videobackup was already mounted! OK, umount and run fsck anyway:
=== root@eureka (/dev/pts/0) /home/grog 12 -> fsck -y /videobackup
** /dev/da0p1
USE JOURNAL? yes
** SU+J Recovering /dev/da0p1
** Reading 33554432 byte journal from inode 4.
RECOVER? yes
** Building recovery table.
** Resolving unreferenced inode list.
** Processing journal entries.
WRITE CHANGES? yes
** 87 journal records in 5120 bytes for 54.38% utilization
** Freed 0 inodes (0 dirs) 0 blocks, and 0 frags.
***** FILE SYSTEM MARKED CLEAN *****=== root@eureka (/dev/pts/0) /home/grog 13 -> mount /videobackup=== root@eureka (/dev/pts/0) /home/grog 14 ->
In passing, maybe fsck should report when there's nothing wrong with the file system, like in this case. But it took me a while to realize two things: firstly, photo backups are written to, well, /photobackup, and secondly /videobackup was on /dev/da0p1. What's the message on about? After mounting, checking showed /photobackup mounted on /dev/da2p1, the partition that it was complaining about, though here too fsck didn't report any errors.
It's a bit late now, but there's something that needs attention in this area.
|
How to win a Nobel prize
|
Topic: politics, opinion | Link here |
It's no secret that Donald Trump is disappointed that he didn't win the Nobel Peace Prize this year, though it was almost impossible from a time perspective. But if the peace in Gaza holds, there's a possibility next year. But Hamas isn't making things easy, including summary executions of people it doesn't like.
OK, says Trump,
If Hamas continues to kill people in Gaza, which was not the Deal, we will have no choice but to go in and kill them,” Mr. Trump wrote in a social media post.
Now isn't that what Israel has been trying to do for the last 2 years?
|
Badly targeted spam
|
Topic: technology, general, opinion | Link here |
Seen on a web page on teevee today, a QR code with the subtitle “Scan this code to prove you are not a robot”. OK, spam, how? I suppose one day something serious will make this kind of mistake; Wise comes to mind.
|
Wimmera duck?
|
Topic: food and drink, opinion | Link here |
“Peking duck” from Luv-a duck today. Here their photo:
How can that be Peking duck? It can't, as our preparations showed. It was soaked in a marinade, which might be interesting in itself:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
But Peking duck should be dry! And even after baking, less than their recommended 15 minutes to avoid burning, we had a skin that was hard to separate from the flesh.
|
|||||||||||||||||||||||
But it didn't taste bad, and I think we'll hold on to the two other packages we have—they will keep until February. And it's interesting to note that they were sold as “Peking flavoured duck breasts”, at least on the packaging. The overview page doesn't mention “flavoured”, but it shows that they two other Peking duck offerings; this one seems to be only for ALDI. Should we try them? I think not.
| Sunday, 19 October 2025 | Dereel | Images for 19 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Eradicating vermin
|
Topic: animals, general, opinion | Link here |
Today as one of the days where Bruno went outside at 6:00. When I got up at 8:30, I found something unexpected:
|
|||||||||||||||||||||||
Closer up it looked like this:
|
|||||||||||||||||||||||
And yes, its throat had been bitten through:
|
|||||||||||||||||||||||
It must have been Bruno. He was no longer interested, and Mona's interest was marginal:
|
|||||||||||||||||||||||
So I gave it to Larissa, who made short work of it:
|
|||||||||||||||||||||||
Should we feed her normally in the evening? I thought yes, and how about that, Lara ate it all.
|
|||||||||||||||||||||||
In the evening Yvonne made a pretty entrée with eggs and lumpfish “caviar”. But she put it on the table a little too early. Later we saw:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
All gone except the decoration. Who was it? The dogs had gone away, but based on their reactions, I think it was Lara. She really does have an appetite.
|
Diary GAU
|
Topic: technology, language, general, opinion | Link here |
I keep my diary in one file per month; this month it's diary-oct2025. In addition, I keep the last two days in a file diary.php, and that's where I write the new entries. Then I copy the entire diary.php into the month's file (so that any updates to the first day get copied). Then RCS ci, sync to external web sites, and I'm done.
This month was marginally different, due to the fictional entries on 15 October, requiring a bit of modification. But later I discovered that I had lost the entries!
That's one of my nightmare situations, ever since I discovered that I had lost the entries for 11 and 12 June 2001. Not to worry this time: I still had the entry in diary.php. But it happened again the next day! By that time I had removed the entries in the main file. I had to go to a web server to get the previous contents.
And then it happened a third time! Am I losing my marbles? Things became clearer when I modified my diary entry for 19 October 2010. Those changes also disappeared! And in this case, I had to type them in again.
What's going on? I still don't know for sure, but it seems that my RCS ci from Emacs is to blame: it doesn't always succeed, and I am so used to it that I didn't check. Clearly I'll check now.
And GAU? A German term („Größter anzunehmender Unfall“, meaning roughly “worst case scenario”), derived from atomic power plant technology and more popular in Germany than the plants themselves.
|
Kebabs again
|
Topic: food and drink | Link here |
The main course today was chicken kebabs, like a year ago today. Nothing spectacular, except that this time we only made half as much, and they were finished earlier than expected, by about 2 minutes.
| Monday, 20 October 2025 | Dereel | Images for 20 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
ABC Ballarat news
|
Topic: technology, general, opinion | Link here |
During my morning ablutions I read various news sources on my mobile phone. One of them is ABC news, which I read mainly to get local news. It's not a good app; badly structured, no dates to the articles, and in the case of local news, it's of no use at all:
|
|||||||||||||||||||||||
There are always three articles, though they seldom have anything to do with Ballarat. In this case there are two sporting articles somewhere, not in Ballarat, though I didn't check where: there are no significant sporting events in Ballarat. The third one, the aviation disaster, happened 75 years ago, so it's hardly news. and it proved to be in South Australia. Why do I bother?
|
Exploring Udon
|
Topic: food and drink, opinion | Link here |
I have two different kinds of udon noodles, and I have no idea how to cook them. Somehow I seem to have missed the boat with Japanese cooking.
Today I started with the ALDI Udon, conveniently packaged in 1½ portion bags. First, how long do you cook? The Hokkaido Udon say “boil until cooked”, or maybe nothing at all:
|
|
||||||||||
|
|
||||||||||
The ALDI noodles, with their trademark illegible white on pale green recommend 4 to 5 minutes:
|
|
|||||||||
Boiled or not boiled? They're too polite to say. It proves to be necessary just to separate the noodles (“soften”). And yes, 4 minutes were plenty.
OK, how do you fake a Japanese dish? Shiitake mushrooms, miso. Oh. Where's the miso? I couldn't find any. All I found was this package, given to me by Jane Ashhurst:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I thought it might be Miso, but Google Translate came up with various translations, none of them very helpful. But it seems to be a shiromiso mixture, and since it has already expired (in February) it was time to use it.
So, the recipe:
| quantity | ingredient | step | ||
| 7.9 g | Dried shiitake mushrooms (2) | 1 | ||
| 10 g | red onion | 2 | ||
| 10 g | ginger paste | 2 | ||
| 10 g | garlic paste | 2 | ||
| 22.4 g | Smoked pork belly | 3 | ||
| 46 g | “Sizzling” pork steak | 3 | ||
| 24 g | Miso paste | 4 | ||
| 15.5 g | Light soya sauce | 4 | ||
| 48 g | Tauge | 4 | ||
| 160 g | Cooked Udon | 5 | ||
The strange quantities were to use up things that were lying around in the fridge. The 7.9 g Shiitake soaked to 35 g.
And the result? Edible, not to be repeated in this form. And it seems that udon isn't really very different from the noodles used in Hokkien Mee, except for the colour.
|
Google Translate again
|
Topic: technology, language, opinion | Link here |
Understanding the content of my suspected miso was not made any easier by the fact that most of the text was in Japanese.
|
|||||||||||||||||||||||
But that's that Google Translate is for, when it wants to cooperate. Today wasn't one of those days. I recognized dashi and a couple of other things, but I didn't get beyond the decision that it must have been some kind of enhanced miso, so I used it anyway.
Sometimes, though, the false positives are amusing in their own right:
|
|
|||||||||
|
|
|||||||||
Another issue is when I'm sitting in front of the TV and want to translate something:
|
||||||||||||||||||||||||
Is that caramel for KL Hokkien Mee? It would be nice to translate the Chinese part of the label. How do I choose the 3x lens on the phone?
Google Gemini was helpful: you can't. Maybe the Xiaomi photo app can do it? Well, it can take the photo above, but that's all. Then I can't translate it. It wasn't until I got to a Real Computer and found a way past Android's “there can only be one” view to copy the image file, that I found the translation: “Kicap Soya Pekat”, just the same as the Malay version underneath. But why is this all so difficult? Aren't I using Android in almost the way the creators envisaged?
|
Oliver? Clinton again
|
Topic: technology, general, opinion | Link here |
Not for the first time, I received 3 messages like this over the last 2 days:
From: Oliver Clinton <oliver.clintone@hotmail.com>
To: "mailer-daemon@lax.lemis.com" <mailer-daemon@lax.lemis.com>
Subject: Question about http://lax.lemis.com/grog/diary-feb2021.php
Message-ID: <PA1P189MB3531872AF2A8107B309B3245F2F5A@PA1P189MB3531.EURP189.PROD.OUTLOOK.COM>
Hello
I’m Olive and I run an advanced AI service called ZeroGPT.com
ZeroGPT is a Free and revolutionary tool to detect if a text was written by an AI tool like Chat GPT or by a human or even a mix of content. ZeroGPT, based on the DeepAnalyse™ Technology developed by our experts, is very reliable with a tested accuracy rate up to 98% which makes ZeroGPT the most advanced and
+powerful ChatGPT detector.
ZeroGPT is one of the most used and famous AI detector tool.
I stumbled upon your website http://www.lemis.com/grog/diary-feb2021.php , and I just have to say: WOW!
I had a quick proposal, I was wondering, would you be interested in featuring a link to my website in your piece regarding ChatGPT, AI and Open AI generated text detector?
I think it could be a great reference for your own article to provide your readers with more valuable information!
Note the URL to which (s)he referred and the confusion over the name. I've seen this before, round the end of December 2023, though I didn't mention it at the time. At the time it was presumably a she, Olive Brandon <olivegptceo@outlook.com>, but the text and URL of the message was identical.
What should I do? AI is becoming increasingly important, and presumably she should have put her text through her tool. But as it happens, I have two similar recent articles in this diary: mine on Bruno's waking habits and Claude's on cat behavior dated a couple of days earlier.
And how about that, GPTZero had no trouble. For my article, “We are highly confident this text is entirely human”, for Claude "We are highly confident this text was AI generated". They go on to say:
We've compared this text to other AI-generated documents. It's similar to the data we've compared it to.
Probability breakdown
The probability this text has been entirely written by a human, AI, or a mix of the two.Most AI detectors are unable to differentiate between text that is either AI or human (e.g., 50% AI probability) or text that is a combination of AI and human (i.e., mixed output). That differentiation is made here.
100% AI generated0% Mixed
Oh. Slight problem. Wrong tool! Olive? was too polite to include a reference to her/his ZeroGPT, and I accidentally found GPTZero instead. OK, we can try with ZeroGPT:
|
|||||||||||||||||||||||
That's not nearly as clear. The 100% certainty has dropped to only 46%! “Your text is most likely human”. Add more text? Yes, that helps. Now it's only 35% likely that Claude's text is AI.
|
|||||||||||||||||||||||
What about the others? How about Olive?? Clearly it's generated in some form, since the text hasn't changed in 2 years, only her/his name. Yes, she/he is mainly human, only 12% AI:
|
|||||||||||||||||||||||
And myself? Almost as human as Olive?, only 21% AI:
|
|||||||||||||||||||||||
Sorry, Olive?, that's not enough, even if there were nothing better available. But turn the name around (where do they get these names from?), and GPTZero does it right. Why bother with ZeroGPT? As the Germans say, „Das ist Null“ (“that is zero”, meaning useless).
|
More pain?
|
Topic: health | Link here |
It seems that people of my age frequently have nagging pain. I don't. But today I had a slight pain in my head. Where in my head? I don't know. I thought it might be toothache, but it wandered and ended up at the top of my skull. Then it went away again. What is it?
|
VicRoads: still no invoice
|
Topic: general, technology | Link here |
It's been over a month since VicRoads sent Yvonne an invoice for the registration of her new car, due on 25 October. Full price, no concession applied. OK, request concession, which was duly granted after what seems an instant for VicRoads, only 3 days:
Transaction reference number: RCA0000830352
Thank you for your concession application for your vehicle registration ZWT400. The concession rate has been successfully applied to the vehicle. Please do not pay your registration until the change is displayed within your myVicRoads account, this may take up to 24 hours. If your vehicle registration has already expired and you need to drive your vehicle, please call 13 11 71 during business hours to pay your concession registration renewal by phone.
That was on 18 September, and it seems that the 24 hours have still not elapsed. Instead I keep getting invoices for double the sum, sent from a different email client. Left hand, right hand syndrome? The last one was on 15 October. And still no corrected invoice! Sent them a message, which they acknowledged, but so far did not act on again.
| Tuesday, 21 October 2025 | Dereel | Images for 21 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Duck noodles
|
Topic: food and drink, opinion | Link here |
It's not easy to find duck round here, but I had some “Peking Duck” left over from Saturday, along with a lot of fatty marinade. Can I use it for breakfast? Yes!
|
|||||||||||||||||||||||
I didn't make a recipe for the dish; noodles are becoming more and more like nasi goreng, where I put in whatever is available. The good discovery here is that the duck marinade was enough by itself, though I also put in choi sam, fried duck skin and fried dòufu.
|
VicRoads: left hand, right hand
|
Topic: general, technology, rant, opinion | Link here |
Still no response from VicRoads. Yvonne's rego expires on Saturday. OK, time to ring up. Another horrible voice non-recognition menu; after 5 minutes I discovered that it seems that saying “consultant” to the main menu works, and I was connected to Morgan.
Morgan was a fount of knowledge, much of which contradicts what I have heard so far. He can't talk to me out of respect for Yvonne's privacy. I tried to point out to him that he doesn't need to give me any information, just look at the matter and react. But that's not in their rule book.
OK, connect me to your supervisor. One moment, please. Sorry, no supervisor available (they're unsupervised). How do I enter a complaint? Wait until the end of the call and I can make my complaint.
But after that he was a little more cooperative. He just needed to know that Yvonne was there, and then I could do the rest. So in the end I got Yvonne to give him her mobile phone number, and he sent a 6 digit PIN to her mobile phone. Anybody who stole her phone and had a female to hand could have “authenticated” her.
And then the reason: she already has a concession registered for the Holden, and There Can Only Be One. He didn't see anything wrong in their handling where they had confirmed in writing that the concession had been applied. I have two choices (apart from paying the full amount):
At the end of the call I was asked to give my opinion of how well the issue had been resolved. Very badly. Say a few words <beep>. So I said a few words. How do you confirm things? Press #. Another beep. Press 1. Some message thanking me for what I said. What actually got recorded?
So, fighting their web site again, found the forms that I needed to fill out. The transfer form was relatively easy, but somewhere I saw that I would still need to pay a transfer fee, which may have been round $47, but it wasn't clear. And we would need to identify ourselves with two documents, A and B. A must be a passport (long expired and thus invalid) or original of birth certificate, something that neither of us have ever seen. In Yvonne's case it was issued by the Third Reich and replaced by the DDR version some time later, and of course both were in German. But more digging shows that there are alternatives, such as a driver license. Why must I dig to find that? Document B is simpler; we have many, but in this case our pensioner cards seem appropriate.
More questions: was this form helpful? No, of course not.
|
|||||||||||||||||||||||
OK, tried again. Same thing with the text the other way round. Tried a total of 10 times with alternating texts. I suspect what they're really trying to say is that I tried to enter the comment more than once.
But somehow things seem stupid. Original documents, particularly birth certificate. Oh, alright, you can show your driver license (which VicRoads has issued to me twice). Original marriage certificate. Oh, alright, you don't need to be married, just de facto, and you can confirm it with a statutory declaration. Why the difference in complexity?
OK, bite the bullet. Print the transfer form, conveniently in PDF form. My printer made junk out of it. First I needed to reprocess it through xpdf, after which I could print.
Then print two statutory declarations of their devising, including driver license number. Yes, that prints with no problems, but I can only enter one line, no line breaks allowed, which greatly limits what I can say. And what do they want to say? As I put in my feedback, they should have said what they wanted to find, and presumably not “VicRoads is completely incompetent”.
A whole afternoon wasted! None of this would have been necesssary if we had registered the Toyota in my name.
|
Gout?
|
Topic: health, opinion | Link here |
I've had mild pain from the big toe joint of my left foot for a day or so. A typical symptom of gout. I've been there before and treated it with indometacin. But the stuff I have expired 2½ years ago. Should I try anyway? Google Gemini suggests that it might not be as effective, but shouldn't do me any harm. But let's wait if it doesn't go away by itself.
| Wednesday, 22 October 2025 | Dereel → Ballarat → Dereel | Images for 22 October 2025 |
| Top of page | ||
| previous day | ||
| next day | ||
| last day |
|
Disk backup issues?
|
Topic: technology, opinion | Link here |
Seen in my system log this morning:
dump -2uf - / | nice zstd -T8 > /dump/teevee-FreeBSD/2/root.bz2
mv: rename /dump/teevee-FreeBSD/2/root.bz2 to /dump/teevee-FreeBSD/2/root.0.bz2: Input/output error
DUMP: Date of last level 1 dump: Sun Oct 19 04:00:21 2025
DUMP: Dumping /dev/ada0p2 (/) to standard output
/home/local/bin/dodump: cannot create /dump/teevee-FreeBSD/2/root.bz2: Input/output error
DUMP: mapping (Pass I) [regular files]
What's that I/O error? I've seen that before, some NFS bogon. But no, umounting and mounting didn't help. The disk had gone away:
=== root@eureka (/dev/pts/0) /home/grog 22 -> l /dump
ls: .snap: Device not configured
ls: .sujournal: Device not configured
ls: Iam: Device not configured
ls: Log.log: Device not configured
...
total 1
drwxr-xr-x 5 grog wheel 512 20 Oct 08:57 distress-Microsoft
drwxr-xr-x 12 root wheel 512 10 Jun 2023 eureka-FreeBSD
...
Why are some directories there and others not? Directory caching. The disk device had gone. Disconnecting and reconnecting the cable was enough, though I had to fsck.
What happened? Clearly it was between the backups of the main machines (round 21:00) and tiwi and teevee (4:00). And sure enough, in /var/log/messages:
Oct 22 04:00:00 eureka kernel: (da1:umass-sim1:1:0:0): READ(10). CDB: 28 00 dc 7e e2 00 00 00 08 00
Oct 22 04:00:00 eureka kernel: (da1:umass-sim1:1:0:0): CAM status: CCB request completed with an error
Oct 22 04:00:00 eureka kernel: (da1:umass-sim1:1:0:0): Retrying command
Oct 22 04:00:02 eureka kernel: ugen0.7: <Western Digital> at usbus0 (disconnected)
Oct 22 04:00:02 eureka kernel: umass1: at uhub2, port 18, addr 6 (disconnected)
Oct 22 04:00:02 eureka kernel: (da1:umass-sim1:1:0:0): READ(10). CDB: 28 00 dc 7e e2 00 00 00 08 00
Oct 22 04:00:02 eureka kernel: (da1:umass-sim1:1:0:0): CAM status: CCB request completed with an error
Oct 22 04:00:02 eureka kernel: (da1:umass-sim1:1:0:0): Retrying command
...
Oct 22 04:00:02 eureka kernel: (da1:umass-sim1:1:0:0): CAM status: CCB request completed with an error
Oct 22 04:00:02 eureka kernel: (da1:umass-sim1:1:0:0): Error 5, Retries exhausted
Oct 22 04:00:02 eureka kernel: g_vfs_done():da1p1[READ(offset=6039227502592, length=4096)]error = 5
Oct 22 04:00:02 eureka kernel: g_vfs_done():da1p1[READ(offset=1894043070464, length=4096)]error = 5
There are a couple of strangenesses there. Firstly, normally I get a message like
Oct 22 03:06:59 eureka kernel: (da1:umass-sim1:1:0:0): SCSI sense: NOT READY asc:4,1 (Logical unit is in process of becoming ready)
Oct 22 03:06:59 eureka kernel: (da1:umass-sim1:1:0:0): Polling device for readiness
That is strange in itself, because nothing should have been talking to the drive at the time. Was it still active at 4:00?
But the other one was that the messages continued after the drive was disconnected, though for less than 2 seconds. One way or another it looks as if it's related to power on. I repeated the dump and it completed without error.
|
VicRoads pain: getting there
|
Topic: general, technology, opinion | Link here |
Off today as planned to visit VicRoads in person in Ballarat. They have moved now, building a new hub in what used to be the car park of the public library. I recall some discussion in the media about the matter at the time, but the government assured people that there would be enough parking for all the additional services. Instead, we discovered, they had not just built on the car park, but also eliminated the street parking spaces. There can't be more than a quarter as many parking spaces there as 10 years ago, though the demand has risen. Here a view from the east, looking south-west, for some reason the newest I could find at Google Maps:
|
|||||||||||||||||||||||
Of those parking spaces, only one row remains. From the other side, probably half have been removed, as these views, also from Google Maps and in tasteful reverse order chronlogical sequence show:
|
|||||||||||||||||||||||
As a result we had to park at the railway station, over 400 m away, and find our way in. It wasn't easy. Inside the walkway we found these two entrances:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
After some searching through the “artwork” found that one included the URL (in ALL CAPS) VICROADS.VIC.GOV.AU (and thus invalid), so we chose that rather than GOV HUB. What do these words mean is a hub, anyway? Yvonne really hadn't heard the term before. The OED says for Gov:
Now chiefly U.S. 1630– Chiefly preceding a name: = governor n. 6.
And hub? That has a more conventional meaning:
1652– The central solid part of a wheel, fan, propeller, etc., to which the axle is fixed, and from which spokes, blades, etc., typically radiate.
Doesn't that help? It has other meanings, of course. From the summary:
I. A lump or protuberance.I.1. A sharply protruding piece of ground, a hummock; a mass or…I.2. A lump or mass of something, in various specialist and…II. A central component of something.II.3. Apparently: the centre or boss of a target. Obsolete.Both…II.4. The central solid part of a wheel, fan, propeller, etc., to…II.5. That which occupies a position or performs a function…II.6. Chiefly North American. Plumbing. A flared or widened…
So which of these describe the “VicRoads hub”? On the face of it, none of them. II.5b states that it can mean the city of Boston. But it seems that it's II.5.a:
That which occupies a position or performs a function analogous to that of the hub of a wheel; a centre, focal point, or nexus.
Most commonly used of something which is (physically) situated centrally with regard to a region, community, etc., around which (in a physical or abstract sense) motion or activity takes place, or which has a (physical or abstract) connection to or association with peripheral components of a network.
OK, so the term exists and can be vaguely applied to where we went. But Yvonne's not stupid: she had just never heard the term before. Wouldn't it make more sense to find terms that are generally understandable?
|
VicRoads pain: done!
|
Topic: general, technology, opinion | Link here |
So finally we found our way to VicRoads, armed with lots of documents as Morgan and the web site had indicated. But he was the right hand. Were they here the left hand? My first document was a printout of their mail messages of 18 September and 14 October. The first read:
Transaction reference number: RCA0000830352
Thank you for your concession application for your vehicle registration ZWT400. The concession rate has been successfully applied to the vehicle. Please do not pay your registration until the change is displayed within your myVicRoads account, this may take up to 24 hours.
Presented that to the consultant, who checked it, confirmed that she had now finally applied the concession, but the confirmation could take up to 2 days. Not a problem: she took Yvonne's money and a card fee of $1.92, which she did not mention, and gave her a receipt. It couldn't have taken more than 5 minutes. Done! It was so fast that Yvonne asked me “what about the rest?”. But that's it! Until they discover she has two concessions, which will be interesting.
What a load of idiots! But we didn't do anything wrong. We're both entitled to concessions, and now we have them.
| Thursday, 23 October 2025 | Dereel | Images for 23 October 2025 |
| Top of page | ||
| previous day |
|
Huevos rancheros con arepas?
|
Topic: food and drink, opinion | Link here |
A couple of years ago Yana brought me some “masa multipreparacion (de maiz amarillo)”, a kind of maize flour, which I have used to make tortillas. But it's originally intended for making arepas, something I had never heard of before.
But last week I found deep-frozen arepas at the Indo-Asian groceries, and bought a packet. It was fun separating them, requiring partial defrosting and then re-freezing:
|
|||||||||||||||||||||||
Today we ate huevos rancheros for breakfast. They're normaly made with tortillas, but it would be interesting to see what it's like with arepas. They took much longer to brown, but when they did, they looked perfectly normal:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
Only: they were far too hard. You can't cut them easily with a knife, at least not the way I cooked them. There was also less flavour, so I won't try that again. What do I do with the remaining arepas? Find out more details about they way they're eaten in Colombia.
|
Garden flowers in mid-spring
|
Topic: gardening | Link here |
It's a month after the equinox, time for the monthly garden photos. Today I had a companion:
|
|||||||||||||||||||||||
Every time I do this, I note how much worse it looks than it used to. It's not helped at the moment by the fact that our lawnmower is—once again—out of service (torn drive belt). But apart from that things look worse every year. A typical example is the remaining clematis that Nick Macdonald destroyed last year. Before that it was starting to form buds:
|
||||||||||||||||||||||||
But now all I have is
|
|||||||||||||||||||||||
That's much less than I expected. It should be flowering by now.
Other signs of death and destruction include a large tree on Corey Spiter's house to the south:
|
|||||||||||||||||||||||
That's due to the heavy winds we had lately.
Four months ago Yvonne went to a lot of time and expense to plant a number of trees:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I had my doubts, especially since they were large trees planted far too close together. But I wasn't expecting complete destruction:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
That may have been due to the exceptionally dry weather, but I'm still surprised.
And our 17 year old tree fern is still alive, but not doing well:
|
|||||||||||||||||||||||
What can have caused that? The ginkgo biloba that we bought at the same time did well, but we left it at Kleins Road. The new one is only 10 years old, but it's not even as big as when we bought it:
|
|||||||||||||||||||||||
That's the tiny thing holding on to the plastic dropper.
Looking at the plants that we bought when at that time, the only other one that has survived is the Alyogyne huegelii, which has been damaged multiple times, but manages to come back:
|
|||||||||||||||||||||||
One sign of the times is the number of drosera plants that have sprung up:
|
|||||||||||||||||||||||
And clearly, despite all attempts, we have irrigation problems. Many of our hebes are doing well:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
But others clearly suffering from lack of water:
|
|||||||||||||||||||||||
|
|||||||||||||||||||||||
I'm getting too old for doing this myself, and I can't find anybody who can do it right.
Will the outside Hibiscus rosa-sinensis survive?
|
|||||||||||||||||||||||
We'll see what happens; it has been remarkably resilient in the past.
Do you have a comment about something I have written? This is a diary, not a “blog”, and there is deliberately no provision for directly adding comments. It's also not a vehicle for third-party content. But I welcome feedback and try to reply to all messages I receive. See the diary overview for more details. If you do send me a message relating to something I have written, please indicate whether you'd prefer me not to mention your name. Otherwise I'll assume that it's OK to do so.
| Top of page | Previous month | Greg's home page | Today's diary entry | Greg's photos | Copyright information |
