Viewing profile — koverstreet

The maturity of leadership in China seems to be on a whole different level from the U.S. Lots of companies in the U.S. have fallen victim to that syndrome, but if you used the word…

U.S. border agents really are just worse. Much worse. (I can't say what racial profiling adds to that, I can only speak to my own experiences). I've been routinely grilled and exte…

I'm not sure if the complexity is at the neuron level. It's clearly possible; we see some pretty complex behavior from single celled organisms - Stentors - and there were the exper…

bcachefs is slowly working up to what you're describing - describing what you want and letting the filesystem sort it out. We're basically there for local storage, and other people…

> More broadly, the predictive brain model would suggest that all of the brain, not just the neocortex, is dedicated to prediction. What would you say makes LLMs similar to the neo…

That's fundamental to how anything that compresses/understands the world has to work, in the Kolmogeravian sense. That's why people denigrate LLMs as being just "next token predict…

Yeah, there's some beautiful math underlying what LLMs are doing, and it's the same math our neocortex runs on.

The mm people are increasingly hostile to any method of handling OOMs (like, just failing the allocation) besides the OOM killer - it's become very dominated by the hyperscalars an…

The point is that the "outbox pattern" is not an atomic transaction. You fundamentally don't have those in the distributed world, via the CAP theorem, and if you want anything clos…

The certainly don't teach you that in business school :)

"AI girlfriend" is something the trolls invented. I've posted code and research - that's how you know they're trolls, they make stuff up anyways :)

Are you forgetting the nitrogen? :)

We're in the middle of a huge spike in LLM discovered security vulnerabilities, which means not everything will get assigned a CVE, a lot of people are watching repositories to loo…

100% - but that's where writing regression tests when people find things really helps with the stress levels of future-you :)

If package maintainers were always fine upstanding package maintainers as you imagine them to be I wouldn't be complaining, but I have in fact had Debian ship my software and screw…

You definitely need different channels for high priority fixes and normal releases, stable and testing releases and all that. But two years is impractical and Debian gets a ton of …

You're going to have to update production at some point, and delaying it to once every 2 years is just deferred maintenance. And you know what they say about that... So when you do…

Well, my workstation runs Debian sid, and all the newer stuff runs NixOS... But that does nothing for people who write and support code Debian wants to ship - packaging code badly …

No, that's exactly the thing to complain about. That whole model dates to before automated testing was even really a thing, and no one knew how to do QA; your QA was all the people…

It seems to me you're style over substance then.

That's pretty much been my day - today was genuinely bad, and I've been putting up with a lot of this lately. Now on Qwen3.5-27b, and it may not be quite as sharp as Opus was two m…

https://transformer-circuits.pub/2026/emotions/index.html At the actual inference level temperature can be applied at any time - generation is token by token - but that doesn't mea…

It's how temperature/top_p/top_k work. Anthropic also just put out a paper where they were doing a much more advanced version of this, mapping out functional states within the mode…

Technically speaking, models inherently do this - CoT is just output tokens that aren't included in the final response because they're enclosed in tags, and it's the model that dec…

I'll have a look. The CoT switch you mentioned will help, I'll take a look at that too, but my suspicion is that this isn't a CoT issue - it's a model preference issue. Comparing O…