Hacker News: solomatov

New comment by solomatov in "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"

solomatov — Thu, 09 Jul 2026 22:28:22 +0000

Thanks for sharing.

New comment by solomatov in "Postgres rewritten in Rust, now passing 100% of the Postgres regression tests"

solomatov — Thu, 09 Jul 2026 21:07:32 +0000

Super impressive! Is it possible for you to share your methodology of using LLMs?

New comment by solomatov in "The short leash AI coding method for beating Fable"

solomatov — Fri, 03 Jul 2026 14:07:07 +0000

I tried a similar approach before, but it didn't work for me. I didn't get a lot of speedup if any from it. IMO, to get productivity you need some kind of YOLO mode (in a sandbox).

IMO, the goal should be to outsource as much work to the model, as possible, while minimizing effort required to understand and review what is did. For example: ask the model to find out why a bug happens, figure out proof of concept for thing X, incrementally optimize something, do a well specified refactoring with some guide, and similar things.

IMO, what people say about creating loops is a very similar thing. You maximize the work done by the model, while minimizing the amount you need to do to control it.

New comment by solomatov in "Tell HN: Mojo is becoming open source"

solomatov — Sat, 27 Jun 2026 16:56:34 +0000

Did they mention the license?

New comment by solomatov in "AI is slowing down"

solomatov — Mon, 08 Jun 2026 17:32:33 +0000

> that he doesn't really understand how inference works from a technical perspective

Could you share what tells about it? I.e. where he was wrong about it?

New comment by solomatov in "AI is slowing down"

solomatov — Mon, 08 Jun 2026 17:27:28 +0000

> progress was slowing

Do you think it's not slowing? Do I miss anything really important?

My understanding is that we have now is incremental improvement on thinking models which appeared more than a year ago. Of course, a breakthrough might happen, but I don't see one yet.

New comment by solomatov in "Anthropic/OpenAI may be spending more than $1000 for every $100 you pay them"

solomatov — Sun, 07 Jun 2026 13:41:08 +0000

Hopefully we will have more information about these companies when Anthropic IPO filing become public. There's too much speculation without them.

New comment by solomatov in "GitHub Copilot App"

solomatov — Tue, 02 Jun 2026 20:53:29 +0000

Personally, I thought about it as next gen vscode

New comment by solomatov in "GitHub Copilot App"

solomatov — Tue, 02 Jun 2026 19:00:05 +0000

So, it's not open source?

New comment by solomatov in "I think Anthropic and OpenAI have found product-market fit"

solomatov — Thu, 28 May 2026 00:53:51 +0000

> but there is so much evidence to point to this not happening

Could you explain this?

New comment by solomatov in "I think Anthropic and OpenAI have found product-market fit"

solomatov — Wed, 27 May 2026 23:24:47 +0000

>For coding you always want to go with the best model in the category, not something that would be the best model if we went 1 year back which GLM 5.1 is, and I'm saying that as a big fan of GLM cause I run a translation site where GLM is good enough for the price.

Currently, the difference is substantial, but what happens if capabilities saturate?

New comment by solomatov in "An OpenAI model has disproved a central conjecture in discrete geometry"

solomatov — Wed, 20 May 2026 19:36:39 +0000

How central is it in the discrete geometry? Could anyone with the knowledge in the field reply?

New comment by solomatov in "OpenAI president forced to read his personal diary entries to jury"

solomatov — Wed, 06 May 2026 13:43:41 +0000

Could you share links about this? When it turned into a different interpretation?

New comment by solomatov in "Microsoft VibeVoice: Open-Source Frontier Voice AI"

solomatov — Tue, 28 Apr 2026 15:35:13 +0000

It would have been better if they provided not just weights, but also some frontend where it is usable as is.

New comment by solomatov in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

solomatov — Mon, 20 Apr 2026 18:37:04 +0000

>but I have seen the local 122b model do smarter more correct things based on docs than opus

Could you please share more about this

New comment by solomatov in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

solomatov — Thu, 16 Apr 2026 22:58:06 +0000

Just curious, the fixes are not about weights but about templates, am I right?

New comment by solomatov in "Qwen3.6-35B-A3B: Agentic coding power, now open to all"

solomatov — Thu, 16 Apr 2026 17:34:10 +0000

Did anyone try it and Gemma 4? Does it feel that it's better than Gemma 4?

New comment by solomatov in "Gas Town: From Clown Show to v1.0"

solomatov — Tue, 14 Apr 2026 21:11:45 +0000

I mean not how to do it, it's not that hard, but how to be productive with it.

New comment by solomatov in "Gas Town: From Clown Show to v1.0"

solomatov — Tue, 14 Apr 2026 20:15:39 +0000

Does anyone has any tips for starting with Gastown? I am comfortable with couple of agents running, but not yet comfortable with what Gastown offers.

New comment by solomatov in "The human cost of 10x: How AI is physically breaking senior engineers"

solomatov — Tue, 14 Apr 2026 16:42:42 +0000

>I’m not sure what you mean by keep it in your head?

If the project I work on is large enough, it takes me some time to get everything I need to understand for review into the short term memory. If it's small enough, it's less of a problem for me.