Hacker News: tsoj

New comment by tsoj in "Born Against, or why hobby programming communities are against LLM usage"

tsoj — Wed, 05 Aug 2026 20:23:48 +0000

what is this swindle

New comment by tsoj in "Born Against, or why hobby programming communities are against LLM usage"

tsoj — Wed, 05 Aug 2026 20:23:18 +0000

wtf the emoji didn't show up

New comment by tsoj in "Born Against, or why hobby programming communities are against LLM usage"

tsoj — Wed, 05 Aug 2026 20:23:05 +0000

New comment by tsoj in "Ask HN: Discrepancy between Lichess and Stockfish"

tsoj — Tue, 13 Jan 2026 23:34:18 +0000

I don't work on Stockfish, but I can suggest using ShashChess instead. It is Stockfosh, but on top of that, it has been improved to capture the spirit of the human ingenuity and creativity.

New comment by tsoj in "Less is more: Recursive reasoning with tiny networks"

tsoj — Wed, 08 Oct 2025 01:23:16 +0000

The TRM paper addresses this blog post. I don't think you need to read the HRM analysis very carefully, the TRM has the advantage of being disentangled compared to the HRM, making ablations easier. I think the real value of the arcprize HRM blog post is to highlight the importance of ablation testing.

I think ARC-AGI was supposed to be a challenge for any model. The assumption being that you'd need the reasoning abilities of large language models to solve it. It turns out that this assumption is somewhat wrong. Do you mean that HRM and TRM are specifically trained on a small dataset of ARC-AGI samples, while LLMs are not? Or which difference exactly do hint at?

New comment by tsoj in "Learning to Reason with LLMs"

tsoj — Thu, 12 Sep 2024 19:14:52 +0000

Yeah, humans are very similar. We have intuitive immediate-next-step-suggestions, and then we apply these intuitive next steps, until we find that it lead to a dead end, and then we backtrack.

I always say, the way we used LLMs (so far) is basically like having a human write text only on gut reactions, and without backspace key.

New comment by tsoj in "AI solves International Math Olympiad problems at silver medal level"

tsoj — Thu, 25 Jul 2024 16:38:47 +0000

This is NOT the paper, but probably a very similar solution: https://arxiv.org/abs/2009.03393

New comment by tsoj in "Will Carbon Replace C++?"

tsoj — Thu, 09 Mar 2023 01:02:45 +0000

The thing is, Sutter's approach is much more sensible when looking at real world adaptation. You can start using the cppfront transpiler, and importantly, if it doesn't work out, you can just use the C++ code generated by cppfront (which Herb Sutter said is meant to be idiomatic and human-readable). From a risk perspective, a developer will have a much easier time convincing a manager to try using cppfront instead of Carbon.

Maybe once Carbon reaches a stable 1.0 release and has seen some success in production (~2026 maybe?), that point won't be as important, but especially in the beginning it seems to me a deciding factor.

New comment by tsoj in "Mastering Nim – now available on Amazon"

tsoj — Thu, 30 Jun 2022 19:32:28 +0000

And for the stuff that matters, it is usually possible to tinker around enough to get it pretty much as good as Rust or C++.

New comment by tsoj in "Nim vs Rust Benchmarks"

tsoj — Wed, 09 Feb 2022 13:06:11 +0000

> no language with GC gets closer than a 2-3x the time of a non-GC language

This is wrong. At least, it is not true generally. I wrote a 1:1 port of my C++ chess engine, and after a bit of fiddling with compiler options the Nim version was faster. In fact, when using a delayed garbage collector, the program was even faster than when using reference counting.