Hacker News: rowanG077

New comment by rowanG077 in "Recent AI models struggled to match a human algorithmic innovation"

rowanG077 — Mon, 12 Oct 2026 00:05:27 +0000

I would love to see them come up with this. And I will gladly await AI to smash through it in short order.

New comment by rowanG077 in "Recent AI models struggled to match a human algorithmic innovation"

rowanG077 — Sun, 11 Oct 2026 19:36:43 +0000

That's not a definition, that's a gut feeling.

New comment by rowanG077 in "Recent AI models struggled to match a human algorithmic innovation"

rowanG077 — Sat, 10 Oct 2026 22:20:57 +0000

I have heard that before, it's essentially the LLM cannot be creative packaged differently. But it always falls flat because there is just no way to measure it let alone define it. In the end it always give me a vibe of them wanting that to be the case rather than it being it case.

New comment by rowanG077 in "Bevy 0.20"

rowanG077 — Sat, 10 Oct 2026 18:09:03 +0000

You have the model play both versions of the game in the same way at the same time. The equality would of course not come from the model, it comes from your testing harness. You just use the model to automatically play the game. SO you are checking game version A(inputs) == game version B(inputs). Where the AI generates the inputs that play through the game 10 times in different ways for example.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Sat, 10 Oct 2026 18:05:00 +0000

We are talking about practicality here. Not impossibility. "Just some dedicated time for it" essentially means man years of focused effort.

New comment by rowanG077 in "Bevy 0.20"

rowanG077 — Fri, 09 Oct 2026 15:55:31 +0000

You’ve taken my statement, that an LLM can help test a game by running hundreds of hours of gameplay equivalence between versions(which btw means the AI doesn't say "it makes sense", your equivalence checker does), and stretched it into a claim that I’m saying games can be made entirely by LLMs through vibe coding with zero human testing. That’s such a blatant misrepresentation of my argument that I struggle to take your comment in good faith.

New comment by rowanG077 in "Bevy 0.20"

rowanG077 — Fri, 09 Oct 2026 12:17:36 +0000

Sure they can. Make the AI play the game pre and post bevy update. And difference down to a pixel can be flagged. In fact you can get hundreds of hours of testing this way using sub-agents.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 14:33:24 +0000

Go is not higher level. If anything I would consider Rust higher on the abstraction ladder than Go. Or rather it's perhaps better to say that Rust is higher level but can go down to a lower level than Go.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 13:52:43 +0000

Money and time are precisely the point. Things are not practically possible of a X would cost 100K to develop and it's worth was 30K. But now that it costs 2K to develop it is suddenly practically possible.

1. A person building alternatives to photoshop single handedly: https://gizmodo.com/someone-vibe-coded-a-free-knockoff-of-ad...

2. The abundance of game decomps and recomps becoming available. Literally dozens of example in this space.

3. Reverse engineering of obscure software. A ton of oppertunities lie here.

4. As this posts indicate, severely accelerating existing software by re-writing it in language that are not terrible for performance.

5. Analyzing large volumes of unstructured information.

6. Creating one-off engineering and scientific tools.

7. Beating essentially all traditional Linux distribution, see Omarchy.

8. A personal example: I'm remaking the engine of an old game commercial game in rust.

I'm honestly a bit taken aback that this question is even asked. The volume of software is exploding and the power of the individual has increased a hundredfold.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 07:48:45 +0000

I don't see at all that this is stifling love of tech. Sure if you liked to engage in language wars or vim vs emacs or tabs vs spaces then yes that's over. But tech as we know it is currently exploding, a ton of stuff that simply was not practically possible before is now possible.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 06:53:40 +0000

The comment I responded on put forth a generic argument that implied if we can not learn from it it has no value. That is what I was responding to.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 02:01:15 +0000

The point is that it's clearly not just a less maintained, less tested implementation. It's 1.61x faster for one in real world apps, in some case even almost 4x faster.

New comment by rowanG077 in "Port of the TypeScript compiler, checker and lsp to Rust, by LLM"

rowanG077 — Thu, 08 Oct 2026 01:49:26 +0000

Generally building something is not about "What does this teach us?" but rather "What can this be used for?". You don't build a house and as "What does this teach us?". It's honestly almost a perverse question to primarily ask for something that aims to have practical value.

The clear reason this has worth is that it's much faster than TSC.

New comment by rowanG077 in "Navier–Stokes Lost in Translation"

rowanG077 — Thu, 08 Oct 2026 01:16:42 +0000

I would expect it's the other way around. The AI wrote a Proof of NS in lean and write up a NL proof based on the lean one. The authors claim that openAI did NL -> Lean, but that is unsubstantiated.

New comment by rowanG077 in "God of War on PSP, recompiled to WebAssembly and running in the browser"

rowanG077 — Wed, 07 Oct 2026 16:42:17 +0000

You are no longer emulating the CPU but the rest of the system you are absolutely emulating. So I think it's very close to traditional emulation.

New comment by rowanG077 in "Subquadratic 3SUM and Subcubic APSP"

rowanG077 — Tue, 06 Oct 2026 18:02:01 +0000

The interesting thing isn't that we now know they can do math. The interesting is that these problems now can be trivially solved.

The value of LLM is not "Ha curious look what it can do". It's not entertainment.

New comment by rowanG077 in "Germany’s RobCo hits $1B valuation"

rowanG077 — Mon, 05 Oct 2026 23:09:00 +0000

You always have to cost/quality of living if you go that route. Because that's literally what taxes are for. Anyway I don't think it's fair to not include VAT. For every euro you want to utilize(modulo some exceptions) you have to pay it.

New comment by rowanG077 in "Mold Linker Version 3.0.0 Release – Rewritten in Rust"

rowanG077 — Mon, 05 Oct 2026 22:50:01 +0000

When porting things to a new language the last thing you should do is rethink previous design decisions. That is a recipe for disaster.

New comment by rowanG077 in "Anthropic reported diary entry to police, woman faces felony charge"

rowanG077 — Mon, 05 Oct 2026 07:03:38 +0000

That day was yesterday. LLMs from big tech regularly refuse to do what you want.

New comment by rowanG077 in "Results from the ASIC puzzle"

rowanG077 — Sun, 04 Oct 2026 21:46:04 +0000

I think they mean a planned economy in the sense of the Soviet Union. The USA is not that, not even close.