HackerTrans
TopNewTrendsCommentsPastAskShowJobs

andrewchambers

no profile record

comments

andrewchambers
·11 dni temu·discuss
The whole fable fiasco really soured me on Anthropic. This just looks disappointing by comparison.
andrewchambers
·15 dni temu·discuss
This seems like it will have pretty huge negative affects on startups needing to compete with 'trusted partners'
andrewchambers
·15 dni temu·discuss
Small businesses can easily buy them.
andrewchambers
·23 dni temu·discuss
I think they meant keep a low profile from the government, not customers. Anthropic is doing the opposite by loudly asking for regulation.
andrewchambers
·29 dni temu·discuss
deepseek v4 pro is great and open weight.
andrewchambers
·w zeszłym miesiącu·discuss
So this is what 'alignment' looks like to them.
andrewchambers
·w zeszłym miesiącu·discuss
This is not the same as source available - you can fork it, the license didn't change.
andrewchambers
·w zeszłym miesiącu·discuss
I think we need a wiki and/or stack overflow equivalent for agents and humans to collaborate.

Grokipedia seems like the main site that is kind of exploring the concept - though I hope better more powerful ones emerge.
andrewchambers
·4 miesiące temu·discuss
Isn't the obvious solution to not accept drive by changes?
andrewchambers
·5 miesięcy temu·discuss
Thats basically what this guy did. He vibe coded a chat interface.
andrewchambers
·5 miesięcy temu·discuss
Yeah - people are hungry for it. They tolerate the kind of crappy docs and difficulties.
andrewchambers
·5 miesięcy temu·discuss
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.
andrewchambers
·5 miesięcy temu·discuss
I do it with ssh and tmux. I suppose tools could make it better.
andrewchambers
·6 miesięcy temu·discuss
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.
andrewchambers
·6 miesięcy temu·discuss
Test suites just increased in value by a lot and code decreased in value.
andrewchambers
·6 miesięcy temu·discuss
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.
andrewchambers
·8 miesięcy temu·discuss
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.
andrewchambers
·9 miesięcy temu·discuss
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.
andrewchambers
·10 miesięcy temu·discuss
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.
andrewchambers
·10 miesięcy temu·discuss
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.