earino

Basically ibs. Incredibly unpleasant bathroom urgency is the way I would describe it.

I think that's a pretty good guess. I move around different countries a lot so I also assume I can look like a bot farm from multiple source IPs.

However at this point I talk to LLMs more than anyone except probably my wife. As a multiple times immigrant, I can absolutely believe I'm adjusting my speech patterns to its vernacular.

Thanks for the vouching. I don't really understand what I did to anger the algorithms! But yeah, I think that that's the real sticking point. If the value prop of jev is "plug it in anywhere and it generally does smart things" you're absolutely right that Laya is Not A Thing. I've spent a bunch of time working on fine tuning models (i teach a class on it! https://earino.github.io/applied-deep-learning/ using the same ModernBERT stuff!) and so for me, I naturally went: "wait a second, so how good is Jev compared to fixing the problem domain."

Anyways, thanks for the vouching!

The base-model criticism is fair. Laya is weak zero-shot and doesn't have the world knowledge of a much larger pretrained model. Their own site puts the base models at around 0.35 on the typed-decisions benchmark, which is close to random.

I don't think that makes it a dead end. Laya is designed to be fine-tuned for a specific task, and the site reports the fine-tuning gains. The 0.766 number comes from fine-tuning on the benchmark's train split, not from the base checkpoint. They also report that fitting a single temperature scalar per question type cuts expected calibration error from 0.466 to 0.081. That's a large gain, and it only shows up after you specialize the model.

"Peer" is doing a lot of work in that comment. Jev can take on a new task without retraining because it starts with far more knowledge; Laya trades that away to stay small and trainable for a fixed task. So I wouldn't compare base Laya to Jev and stop there. Compare Jev to fine-tuned Laya on the same task and test set, then look at accuracy, latency, cost, calibration, and robustness, depending on which of those matter for the deployment.

Ox bile supplementation was my biggest quality of life change after having my gall bladder removed. I unfortunately waited over a miserable decade before discovering it. I strongly encourage anyone who has had their gall bladder removed to look into this.

Claude going down is how I know I can start messaging with my west coast friends.

Hello Boris! How do I increase the 1 hour prompt cache window for the main agent? I would love to be able to set that to, say, 4 hours. That gives me enough time to work on something, go teach a class, grab a snack, and come back and pick up where I left off.

Two of the authors are engaging on bluesky regarding the "clickbaityness" of the paper:

https://bsky.app/profile/gaborbekes.bsky.social/post/3md4rga...

(Note, I receive a thanks in the paper.)

What joy to bump into you in the comments section! I definitely preferred 5 minutes past, but my calendar was pretty awful.

What was really awful, however, was when your calendar was a random mishmash of starts at :00, :05, :30 and :35 :-)

Built this over the weekend with my wife using Claude Code. Github repo for site is here: https://github.com/earino/nonprofit-ai and github repo for prompt testing harness is here: https://github.com/earino/prompt-harness

Was a really fun weekend project!

Follow up question, can the diff apply and fix json models be run locally as well with octofriend, or do they have to hit your servers? Thanks!

Ok wonderful! Thanks.

I'm trying to set it up right now with lmstudio with qwen3-coder-30b. Hopefully it's going to work. Happy to take any pointers on anything y'all have tried that seemed particularly promising.

This looks very interesting. I wish it came with some guides for using it with a local LLM. I have an MBP with 128gb of ram and I have been trying to find a local open source coding agent. This feels like it could be the thing.

As a proud graduate of MTSU's CS department, I'm so happy to see my school listed here. Even back in the 1990s when I attended there, everyone knew the recording industry program was something special. For a small to medium town, Murfreesboro had an incredible music scene.

I loved getting my bachelor's degree there. Best 9 years of my life :-D

This was a really enjoyable couple of minutes. I was able to find some of the more ancient cities I've visited (Ceuta, for example), and see how they're represented.

Now that we've seen how quickly digitized information becomes un-usuable, it's interesting to reflect that the actual physical Mappa Mundi will far outlive (barring fires/disasters) any of it's digital reflections.

I now live in a 4 story building in Spain and I too miss having BBQs.

What a wonderful article.

I've lived in single family homes and apartments in USA, Switzerland and Spain. I never understood why the apartment buildings in the USA felt so different, and now it makes sense. Even in my 15 story apartment in Zurich, there was a single stair. It made the apartment layouts much better, made it easier to make apartments with a lot more light, and many of the things this article talks about.

Now I live in Spain in a building from the 1960s. A 4 story apartment building, retrofitted in the 1980s with a tiny elevator. It's a really efficient design, though my wife and I have discussed that from an accessibility standpoint, it leaves a lot to be desired.

Now I understand the constraints of apartment designers in the USA a bit better!

ChatGPT now has the ability to do web browsing to search for recent events!

https://chat.openai.com/share/c35e3fd1-d94e-477b-a331-b14384...

I was in Istanbul recently, and what surprised me was the absolute depth of the cities attractions. I stayed in the Kadıköy and Sultanahmet districts, and it was so incredible to walk through a society which had been Monkey Patched through millennia. The runtime behavior of the objects, streets, buildings and the city had been adapted time and time again. Roman temples becoming Churches becoming Mosques becoming Museums, sometimes simply with some new tiles or a freshly laid down carpet. Each layer rich in artifacts. My favorite attraction was the Great Palace Mosaics Museum, some of the most detailed and vibrant mosaics I had ever seen. I hope to return soon.

Congratulations for getting this done. A very small percentage of folks who want to do this actually do it.

My constructive feedback is that the app asked me to register immediately. I didn't really get an idea of why I would get value from it.

Consider giving me a little tour or letting me browse before I have to give you my email address? Thanks and good luck!

> Did you know that you can save ~$62,000 per year per company you work for, tax free (or deferred)?

Do you happen to have a link or pointers?

No worries at all, again thanks for the pointers!

Amazing! Thank you so much for pointing this out to me. It's basically exactly what I hoped to find :-)

Thanks for the pointer! Do you (or your friend) happen to have a link to a sample job post that I may be able to use to identify these opportunities in the future?

I have been deeply fascinated by COBOL ever since 1994. In 1994 I was looking at where to go to college, and the community college near the town I grew up had two "computer" associates programs. One was a program focused on personal computers, and one was a program focused on mainframes. The person I spoke to at the school told me, at the time, that as far as he could tell graduates of both programs got good jobs, but he never saw anyone cross from one to the other. Once the track was picked, the lives and careers diverged. He described the mainframe path as "for going deep into the guts of banks, insurance companies, government and big big companies." It was not a great pitch to give a 16 year old IMO.

I ended up going to neither and went to a traditional CS undergrad at a 4 year state school, and things have been fine ever since. However, on a regular basis, I think about the other life I would have had, if instead I had gotten an associate's in mainframe programming. What would I have done? Where would I have worked? Who even are those folks.

If today I found a COBOL bootcamp that reskilled developers for a career change into COBOL, i may even seriously consider it. An unexplored path that has always been in the back of my head, deep in the guts of the engines of industry.

I do, thanks for asking! I am the proud dad of a 22 year old son :-)

I definitely agree that having a child can be a spectacular forcing function for focus for some. I unfortunately also know folks for whom having a child was the proverbial straw, and whose life fell apart afterwards.

I was running my own company (RFID and industrial automation startup) before him. When I became a dad I found a corporate job. The worry around healthcare costs for a family as an independent were simply too much for me, even back then. All in all, I feel very fortunate in how it all worked out for my family.