brumar

not sure I understand your question, but subagents are used extensively to avoid a large main context window.

Thx for tips. I just saw there are some courses on chess.com, that will be nice to compare claude understanding with Silman commentary as the gold standard.

Edit: I am pushing a small attempt on this position. I fed this one as a screenshot https://www.chess.com/lessons/roots-of-positional-understand... . I forgot to tell that it was black to move but that was fine. The analysis quality seems ok. What puzzles me is that it recognized the Carlsbad structure and talked a bit the plans around the minority attack, not only the correct explanations on g6 and why it should be played. This is where we benefit from positional stuff in the training data.

Good point. I had to tweak a bit the system to get more positional analysis because this is something I wanted too get. I think it's still shying away on this aspect. When it does dwell on it, I feel that when the output describe what should be the plan of both camps, it's quite convincing but only a much stronger player (or me with stockfish) could really assess this.

Anyway I am with you that deep positional appraisal is very hard and we should not expect too much from this set of skills on that front.

Yep, they are quite bad without stockfish. You can test it with the playchess skill in my repo. Maybe 1200/1300, who knows? Still I do think that they can, with enough time, explore multiple variations where they confront their naivety to stockfish and build up a compact picture on why move Y should have been played instead of move X. That was my intuition when building this skill.

No need to apologize. I like reading HN for comments that don't beat around the bush.

It's true that it's costly. I never tried to optimize it. In a way I feel this hacky project doesn't deserve its place on the front page. It's just me hacking around on Claude Code to get something I like. Take it as a proof of concept if you will. I'd be happy to see lighter alternatives.

> Then presenting it as a project or tool of value to share to others is delusional

Here I see a gap in your reasoning. Lazy and costly, sure. But useless, I'm not so sure. In my world, a vibecoded tool can be useful enough to be shared, despite the risks. Claude Code itself is almost entirely written by Claude, according to its creator. Yet I use it every day.

No it does not help the quality of the analysis from what I saw, but it makes the analysis much more interesting, because it can challenge my wrong judgement and answer the questions that I asked myself out loud.

Very interesting project, is Maia used in this platform?

This is crazy. My claude chess stuff is (edit: was) currently near yours on the front page and noticed your post. I have a project very close than yours that I hesitated to share. From a quick glance, we went for a similar approach. I just open sourced it so that you can compare implementation notes. https://github.com/brumar/whiteboard-agents . It's not thoroughly tested but can be interesting to check.

Yes.

Thanks for trying it out! I'd be happy to see how it goes for you and compare our implementation notes if the analysis you got is not too bad.

Very true. I like to think AI somehow optimizes for "efficient vagueness", which is bad news for our brain.

Nonetheless, as many do, I often ask AI to explain me stuff. I know it's not perfect, but it's convenient, it's a trade-off to make.

Not by hand, no, the code was generated with claude code. The readme too, but with some extra efforts to avoid the awful ai generated readme.

It took multiple sessions to get to this result. At first I only generated annotated pgns and standalone html page inspired by lichess. The video generation was the cherry on top, it took few iterations too to fix issues and add markers and arrows. I only use consume the generated video these days, for the moment.

Thanks for sharing! So you gave stockfish to Claude too? Did you try other techniques?

The jury is out for the effectiveness, it's hard to debate this subject. From my cognitive background I know very well how important the generative effect is for learning. Maybe I'll add features that leverage generative/testing effect one day. Anyway, clicking on stockfish branches can be quite a passive activity too if done badly. I don't know how to do that well to be honest. My goal is often to just to understand what I missed, full stop.

For the sycophancy, I can say I did not feel that at all. When stockfish says your move suck, claude would have a hard time saying the opposite (no "you are absolutely right" when I am not).

This what I think too. I also think there are much more refined approaches than the one I tried here. From a cursory look, I saw there are both scientific litterature on the subject of mixing llms and tools like stockfish and some dedicated closed platforms that put that into action.

Let's make clear that I did not spend much time on this project. Ideally I would have tried to put other models into the mix, like maybe Maia to better see the game from a "real player" eyes and pinpoint where expected move and stockfish moves differ.

Anyway, to me, it's good enough to be usable and shared.

That was exactly my estimation when I played "raw" against Opus. But Opus with stockfish as a tool and much time available can, from what I experienced, generate good comments.

Weird, the video is supposed to be embedded. On my chrome desktop it displays properly. EDIT: fixed

I'll add Minimum Description Length to the mix. Under certain definitions and conditions, it equals the Bayesian Information Criterion plus an extra term, which I consider a very interesting result in this "two faces of the same coin" perspective.

But characters only exist when we ask the model about this and it does it best to do this projection if asked. Vision model are richer than that. It "understands" visually a document. If it was only about characters, then there will be no way it beats the traditional pipelines of image->text->extractions or obtain the kind of results we see in this article. Vision models are more than characters recognition and OCR term don't do it justice IMHO.

Tangentially related: I don't think OCR is the right term and I am generally vocal about that. But seeing this unquestioned here, I am wondering if I am the one who is wrong here. Is it ok to call this OCR? To me ocr means text in the end, not visual tokens.

I remember a time where HN was quite critical to the complexity of k8s. After reading top comments, I can see the tide has shifted.

Edit: oh no, so sorry, I am using another project named recall. But not this one. https://github.com/arjunkmrm/recall

Happy user of recall here. I rarely need it as I try to keep conversations small and files-focused. But when I do need it, it brings a lot of value. Sometimes there are conversations where I failed to capture some interesting things. Recall is also very helpful to me to audit my system like when I start to suspect some inefficiencies around some tools (skills, mcps, clis). Recall was efficient to retrieve "tranversal context" required for such audit.

So HR and middle management, legal is ... measuring?

They want to focus on builders and sellers but will support them like robots. A great recipe for disaster.

Legal is measuring too? I can't wrap my head around the reasoning process here. Unless cloudflare is going to be a teal enterprise (from the reinventing organisations book), I don't see how it makes sense.

When all these "bugs" align with /A self interest, it's quite a charitable view to attribute these to negligent vibe coding.

After all, this "mode" was just a system prompt (last time I looked).

A comment overgeneralizing the current comments trend to then write something less conformant.

Also that: I never saw HN being so playful before.

Why not leting upvotes do their thing? I enjoyed this comment.

Thank you!

I get that "landing a prod diff" means "get stuff in production"? I never read this before. Is this slang unique to meta?

For personnal agents like claude code, clis are awesome.

In web/cloud based environment, giving a cli to the agent is not easy. Codemode comes to mind but often the tool is externalized anyway so mcp comes handy. Standardisation of auth makes sense in these environments too.

Same. In my experience, the first plan always benefits from being challenged once or twice by claude itself.