Hacker News: andrewchambers

New comment by andrewchambers in "Redox OS has adopted a Certificate of Origin policy and a strict no-LLM policy"

andrewchambers — Tue, 10 Mar 2026 09:41:45 +0000

Isn't the obvious solution to not accept drive by changes?

New comment by andrewchambers in "I’m joining OpenAI"

andrewchambers — Wed, 18 Feb 2026 09:38:47 +0000

Thats basically what this guy did. He vibe coded a chat interface.

New comment by andrewchambers in "I’m joining OpenAI"

andrewchambers — Mon, 16 Feb 2026 01:25:08 +0000

Yeah - people are hungry for it. They tolerate the kind of crappy docs and difficulties.

New comment by andrewchambers in "I’m joining OpenAI"

andrewchambers — Mon, 16 Feb 2026 00:43:40 +0000

I think it was obvious, yet nobody seemed to have released a version people could actually easily use.

The feature set is pretty simple:

- Agents that can write their own tools.

- Agents that can write their own skills.

- Agents that can chat via standard chat apps.

- Agents that can install and use cli software.

- Agents that can have a bit of state on disk.

New comment by andrewchambers in "The Codex App"

andrewchambers — Mon, 02 Feb 2026 21:54:31 +0000

I do it with ssh and tmux. I suppose tools could make it better.

New comment by andrewchambers in "Scaling long-running autonomous coding"

andrewchambers — Tue, 20 Jan 2026 19:59:53 +0000

I think we agree - getting the llms to understand your intent is the hard part, at the very least you need well specified tests.

Perhaps more advanced llms + specifications + better tests.

New comment by andrewchambers in "Scaling long-running autonomous coding"

andrewchambers — Tue, 20 Jan 2026 11:10:27 +0000

Test suites just increased in value by a lot and code decreased in value.

New comment by andrewchambers in "AI is forcing us to write good code"

andrewchambers — Tue, 30 Dec 2025 09:05:33 +0000

Where did it say the tests need to be hallucinated ?

If you can make good tests the AI shouldn't be able to cheat them. It will either churn forever or pass them.

New comment by andrewchambers in "AirPods libreated from Apple's ecosystem"

andrewchambers — Sun, 16 Nov 2025 04:50:02 +0000

Mark Zuckerberg explicitly called out the airpod pairing being closed as unfair in a semi recent interview, maybe he can throw some dollars that way and get it all working nicely in some meta products.

New comment by andrewchambers in "You can't build tcc from Nixpkgs if you are in the UK"

andrewchambers — Fri, 10 Oct 2025 19:29:33 +0000

Was playing around with the idea of p2p source hosting in package trees like nix and did a little weekend package prototype here of my own here:

https://github.com/magnet-linux/magnet-linux

Not really ready for prime time, but I think I have some interesting ideas there at least.

New comment by andrewchambers in "ABC yanks Jimmy Kimmel’s show ‘indefinitely’ after threat from FCC chair"

andrewchambers — Thu, 18 Sep 2025 01:10:47 +0000

My point isn't really about what is correct or incorrect in this case.

My point is about making it so that you have to actively risk money to push the truth needle in the wrong direction.

New comment by andrewchambers in "ABC yanks Jimmy Kimmel’s show ‘indefinitely’ after threat from FCC chair"

andrewchambers — Thu, 18 Sep 2025 00:46:18 +0000

I've seen a large number of comments online saying the shooter was a trump supporter - I don't really understand where that information comes from.

I feel like this is the sort of thing a prediction market might be able sort out.

New comment by andrewchambers in "Reichstag Fire Decree (1933)"

andrewchambers — Tue, 16 Sep 2025 09:53:31 +0000

Hoping for a polymarket bet so this can be resolved.

New comment by andrewchambers in "AI coding"

andrewchambers — Sat, 13 Sep 2025 20:36:42 +0000

Kind of surprised by this take - I use openpilot often and also use claude code.

I kind of consider them the same thing. Openpilot can drive really well on highways for hours on end when nothing interesting is happening. Claude code can do straight forward refactors, write boilerplate, do scaffolding, do automated git bisects with no input from me.

Neither one is a substitute for the 'driver'. Claude code is like the level 2 self driving of programming.

New comment by andrewchambers in "Zlib-rs is faster than C"

andrewchambers — Mon, 17 Mar 2025 11:37:57 +0000

It's more like letting a wet dog who you are watching closely quickly pass from your front door to the shower.

New comment by andrewchambers in "Schemesh: Fusion between Unix shell and Lisp REPL"

andrewchambers — Sun, 16 Feb 2025 09:28:49 +0000

Author here - thanks for linking - Unfortunately I didn't have time to continue on this for a long while. I am certainly happy if people get inspiration from any ideas and continue on with it.

New comment by andrewchambers in "Recent results show that LLMs struggle with compositional tasks"

andrewchambers — Sun, 02 Feb 2025 12:49:05 +0000

If you haven't tried using them then I am not sure your opinion on them is any good.

New comment by andrewchambers in "Test-driven development with an LLM for fun and profit"

andrewchambers — Fri, 17 Jan 2025 03:50:19 +0000

You don't need microservices for that, just factor your code into libraries that can fit into the context window. Also write functions that have clear inputs and outputs and don't need to know the full state of the software.

This has always been good practice anyway.

New comment by andrewchambers in "AI Is the Black Mirror"

andrewchambers — Sun, 22 Dec 2024 08:59:02 +0000

Using the term 'slop' to deride it for its lack of originality is pretty funny to me.

New comment by andrewchambers in "Reflections on building with Model Context Protocol"

andrewchambers — Sun, 15 Dec 2024 23:16:46 +0000

Thanks for MCP, I think it is sorely needed, it shouldn't take more than a single file shell/python script to teach an llm how to access a resource.