buryat

it's quite useful in a convertible along with the heated steering and the neck warmer taking it roof down on a coldish day

foldable screens

that's quite cheap for 6 trillion requests, that's like 555M for a dollar

The code itself indeed has become cheap but the question still is out whether it solves the right problem. I've shifted my work significantly toward designing more high-level portions where multiple things would interact in somewhat unpredictable manner (read as failure modes) that's where I found the models being quite poor, they do suggest many things to solve these or that problems but in a unity these suggestions miss second order effects. I was quite surprised that models can't hold all of the connected pieces simultaneously to reason about. But once I have a complete design after a week of deliberations and various attempts, the models can produce lots of correct code to cover that. And then another pass starts because they still deviate in implementation of various pieces and once you start questioning those the models start self-correcting. Judging the output is still way faster than writing the code yourself and indeed models still show some cases that slipped once mind. It's a definitive increase in terms of quality and value of the end code no doubt. Whether it can one-shot a complex problem, not really.

Grok since it's likely to include the training data from over a 100 years of autonomous driving + all the space tech included meaning that it might even have some rocket-y stuff

Minecraft is just limited for additional value creation, i.e. it's not a tool for creating more value

Not sure I understand how it's different from a team of sub-agents, what's the difference I'm curious?

Sympathy to engineers and everyone at github, it's good that they're being open even if findings are limited. I'm sure they will figure out the root cause and will publish results to be a learning experience for everyone else

thank you! Learned why DuckDB is named this way

I have a Mac Studio with 512GB Ram and ran models of different sizes to test out how local agents are and I agree that local models aren't there yet but that depends on whether you need a lot of knowledge or not to answer your question, and I think it should be possible to either distill or train a smaller model that works on a subset of knowledge tailored toward local execution. My main interest is in reducing the latency and it feels that the local agents that work at high speeds should be an answer to this but it's not something that someone is trying to solve yet. Feels like if I could get a smaller model that could run at incredible speed locally that could unlock some interesting autoresearching.

interesting approach, thanks for directing me!

Since the classifier would need to have access to the whole log message I was looking into how search is organized for the CLP compression and see that:

> First, recall that CLP-compressed logs are searchable–a user query will first be directed to dictionary searches, and only matching log messages will be decompressed.

so then yeah it can be combined with a classifier as they get decompressed to get a filtered view at only log lines that should be interesting.

The toughest part is still figuring out what does "interesting" actually mean in this context and without domain knowledge of the logs it would be difficult to capture everything. But I think it's still better than going through all the logs post searching.

yeah, I saw Claude Code doing lots of grepping/find and was curious if that approach might miss something in the log lines or if loading small portion of interesting log lines into the context could help. I find frequently that just looking at ERROR/WARN lines is not enough since some might not actually be errors and some other skipped log lines might have something to look into.

And I just wanted to try MCP tooling tbh hehe Took me 2 days to create this to be honest

the patter matcher is interesting to also collapse log lines and compare that between runs, thank you!

In my tool I was going more of a premise that it's frequently difficult to even say what you're looking for so I wanted to have some step after reading logs to say what should be actually analyzed further which naturally requires to have some model

it worked for me