Live data from Hacker News

Scaling long-running autonomous coding

simonwillison.net

111–112 of 112 posts

Re: Scaling long-running autonomous coding

#111

Earlier quoted context omitted.

I'm not sure about what you mean with your first sentence in terms of product. But in general, my guess at an answer(supported by the results of the experiment discussed on this thread), is that: - GenAi left unsupervised cannot write a browser/engine, or any other complex software. What you end-up with is just chaos. - A group of humans using GenAi and supervising it's output could write such an engine(or any other…

That is a wonderful write up. “This is a clear indication that while the AI can write the code, it cannot design software” To clarify what I mean by a product. If we want to design a browser system (engine + chrome) from scratch to optimize the human computer symbiosis (Licklider), what would be the best approach? Who should take the roles of making design decisions, implementation decisions, engineering decisions an…

> That is a wonderful write up.

Thanks.

> what would be the best approach?

I don't know but it sounds like an interesting research topic.

Re: Scaling long-running autonomous coding

#112
post #88
post #29

Earlier quoted context omitted.

Assets are very hard to produce and largely unsolved by AI at the moment.

There's AI based 3d asset generation tools around. For example https://www.meshy.ai/ https://hyper3d.ai/ https://www.sloyd.ai/

Today I learned all you need is some random 3d assets to solve for 'games need assets' problem.
Post reply on HN