Live data from Hacker News

What's the largest software project AI can complete on its own?

epoch.ai

1–10 of 110 posts

Re: What's the largest software project AI can complete on its own?

#3
post #2

I'm curious about that too. I'm building a language with AI, and when I leave the AI running on its own, it keeps generating code in strange directions. I wonder what kind of structure AI-only code would have.

Is it like self driving cars, where 100% non-human code would be arguably safer?

But then it always comes down to having some human who is accountable for verifying the behavior. I think ultimately we just need a better set of languages and frameworks to minimally encode the types of applications we want to build today, so that human comprehension and verification of the source code becomes easier.

Re: What's the largest software project AI can complete on its own?

#4
post #3
post #2

I'm curious about that too. I'm building a language with AI, and when I leave the AI running on its own, it keeps generating code in strange directions. I wonder what kind of structure AI-only code would have.

Is it like self driving cars, where 100% non-human code would be arguably safer? But then it always comes down to having some human who is accountable for verifying the behavior. I think ultimately we just need a better set of languages and frameworks to minimally encode the types of applications we want to build today, so that human comprehension and verification of the source code becomes easier.

How would 100% non-human code possibly be safer?

Re: What's the largest software project AI can complete on its own?

#6
post #3
post #2

I'm curious about that too. I'm building a language with AI, and when I leave the AI running on its own, it keeps generating code in strange directions. I wonder what kind of structure AI-only code would have.

Is it like self driving cars, where 100% non-human code would be arguably safer? But then it always comes down to having some human who is accountable for verifying the behavior. I think ultimately we just need a better set of languages and frameworks to minimally encode the types of applications we want to build today, so that human comprehension and verification of the source code becomes easier.

I've noticed that when only AI writes the code, there are cases where it ends up being unusable by humans. For small code snippets or function-level units, AI is often much better than me. But when I look at the whole picture, AI tends to perform poorly.

Re: What's the largest software project AI can complete on its own?

#7
post #3

Earlier quoted context omitted.

Is it like self driving cars, where 100% non-human code would be arguably safer? But then it always comes down to having some human who is accountable for verifying the behavior. I think ultimately we just need a better set of languages and frameworks to minimally encode the types of applications we want to build today, so that human comprehension and verification of the source code becomes easier.

How would 100% non-human code possibly be safer?

well if driving is supposedly safer when automated, why not code

Re: What's the largest software project AI can complete on its own?

#8
I'm experimenting with large-ish software projects using Claude Fable. The results are surprising to me.

- Project portfolio management software. Good results so far. This is unguided experimentation: Fable researches feature ideas and plans them, then Opus 5 implements them, without me in the loop. The features include things such as an auth server, full-text search, audit logging, resource leveling, HA/DR, IaC, and more.

- FHIR & SNOMED medical software experimentation in demo-only environments. This has mixed results so far. This is guided experimentation: the FHIR specifications and SNOMED specifications are thorough and I'm in the loop. Fable plans OK, but Opus 5 is thrashing a lot, going down many rabbit holes.

Re: What's the largest software project AI can complete on its own?

#10

Earlier quoted context omitted.

How would 100% non-human code possibly be safer?

well if driving is supposedly safer when automated, why not code

It’s supposedly safer than the average driver, not safer than professional drivers.
Post reply on HN