Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A case study in testing with 100+ Claude agents in parallel

imbue.com

Post reply on HN
Print view View original

31–40 of 57 posts

Re: A case study in testing with 100+ Claude agents in parallel

#31

Post by kanjun »

neonstatic wrote: post #29
kanjun wrote: post #28

Earlier quoted context omitted.

Kanjun here, cofounder of Imbue (we put out this blog post, and I'm quite surprised it's on the front page of HN!) The agent orchestration library (mngr) is open source, so we aren't selling anything. There is literally no way for us to make money on it. We shipped it this way instead of trying to monetize because we believe open agents must win over closed / verticalized platforms in order for humans to live freely…

[flagged]

In fact I was just on a walk at the park.

Feel free to come back in 10 years when your brain's been rotted by the equivalent of agent ragebait and the digital infrastructure of your life is trapped in the AI lab agent oligopoly, and we can talk.

Re: A case study in testing with 100+ Claude agents in parallel

#32

Post by neonstatic »

kanjun wrote: post #31
neonstatic wrote: post #29

Earlier quoted context omitted.

[flagged]

In fact I was just on a walk at the park. Feel free to come back in 10 years when your brain's been rotted by the equivalent of agent ragebait and the digital infrastructure of your life is trapped in the AI lab agent oligopoly, and we can talk.

Sure, a computer program generating tokens will enslave me. Thanks for your wisdom.

Re: A case study in testing with 100+ Claude agents in parallel

#33

Post by heavyset_go »

hmry wrote: post #16
petcat wrote: post #13

Earlier quoted context omitted.

Courts ruled that AI works can't be copyrighted https://fairuse.stanford.edu/case/thaler-v-perlmutter/

Please read the link you're citing > The court held that the Copyright Act requires all eligible works to be authored by a human being. Since Dr. Thaler listed the Creativity Machine, a non-human entity, as the sole author, the application was correctly denied. The court did not address the argument that the Constitution requires human authorship, nor did it consider Dr. Thaler’s claim that he is the author by virtue…

An earlier attempt at registering AI creations without AI attribution was rejected by the Copyright Office[1], saying that person in particular needed to make an AI attribution, which they were originally not doing.

In this case, the court is saying AI attribution is not okay, either. There is no way to register copyrights for AI creations.

It's consistent with the Copyright Office's interpretation of copyright law where it holds that it only applies to human creations and doesn't apply to non-human creations, which is what they say AI creations fall under:

> The Copyright Office affirms that existing principles of copyright law are flexible enough to apply to this new technology, as they have applied to technological innovations in the past. It concludes that the outputs of generative AI can be protected by copyright only where a human author has determined sufficient expressive elements. This can include situations where a human-authored work is perceptible in an AI output, or a human makes creative arrangements or modifications of the output, but not the mere provision of prompts.

[1] https://www.copyright.gov/rulings-filings/review-board/docs/...

[2] https://newsroom.loc.gov/news/copyright-office-releases-part...

Re: A case study in testing with 100+ Claude agents in parallel

#34

Post by kanjun »

neonstatic wrote: post #32
kanjun wrote: post #31

Earlier quoted context omitted.

In fact I was just on a walk at the park. Feel free to come back in 10 years when your brain's been rotted by the equivalent of agent ragebait and the digital infrastructure of your life is trapped in the AI lab agent oligopoly, and we can talk.

Sure, a computer program generating tokens will enslave me. Thanks for your wisdom.

You're welcome. To some extent, computer programs deciding what you see next already have: https://www.ted.com/playlists/610/the_race_for_your_attentio...

Re: A case study in testing with 100+ Claude agents in parallel

#35

Post by khazhoux »

Me: has to babysit every feature for hours in Claude Code, building a good plan but then still iterating many many times over things that need to be fixed and tweaked until the feature can be called done.

Bloggers: Here's how we use 3,000 parallel agents to write, test, and ship a new feature to production every 17 minutes in an 8M-LOC codebase (all agent-generated!).

... I'm doing something wrong, or other people are doing something wrong?

Re: A case study in testing with 100+ Claude agents in parallel

#36

Post by jiffy_lubricant »

khazhoux wrote: post #35

Me: has to babysit every feature for hours in Claude Code, building a good plan but then still iterating many many times over things that need to be fixed and tweaked until the feature can be called done. Bloggers: Here's how we use 3,000 parallel agents to write, test, and ship a new feature to production every 17 minutes in an 8M-LOC codebase (all agent-generated!). ... I'm doing something wrong, or other people ar…

> 8M-LOC codebase

I think this is the difference. These toy examples of using parallel agents are *not* running against large codebases, allowing them to iterate more effectively. Once you are in real codebases (>1M LoC), these systems break down.

Re: A case study in testing with 100+ Claude agents in parallel

#37

Post by tossandthrow »

khazhoux wrote: post #35

Me: has to babysit every feature for hours in Claude Code, building a good plan but then still iterating many many times over things that need to be fixed and tweaked until the feature can be called done. Bloggers: Here's how we use 3,000 parallel agents to write, test, and ship a new feature to production every 17 minutes in an 8M-LOC codebase (all agent-generated!). ... I'm doing something wrong, or other people ar…

To an extend you are likely doing something wrong.

I understand that the natural instinct is to correct the output when you see your agent doing something wrong.

That is not productive.

The instinct should be to tweak the agent to do it right.

At this point I am almost not writing any code in an enterprise code base.

Re: A case study in testing with 100+ Claude agents in parallel

#39

Post by khazhoux »

tossandthrow wrote: post #37
khazhoux wrote: post #35

Me: has to babysit every feature for hours in Claude Code, building a good plan but then still iterating many many times over things that need to be fixed and tweaked until the feature can be called done. Bloggers: Here's how we use 3,000 parallel agents to write, test, and ship a new feature to production every 17 minutes in an 8M-LOC codebase (all agent-generated!). ... I'm doing something wrong, or other people ar…

To an extend you are likely doing something wrong. I understand that the natural instinct is to correct the output when you see your agent doing something wrong. That is not productive. The instinct should be to tweak the agent to do it right. At this point I am almost not writing any code in an enterprise code base.

I'm not touching code. I'm trying out the feature, and there's any number of things to tweak (because I missed some detail during planning, or agent made bad assumption, etc).

Re: A case study in testing with 100+ Claude agents in parallel

#40

Post by pinkmuffinere »

tossandthrow wrote: post #37
khazhoux wrote: post #35

Me: has to babysit every feature for hours in Claude Code, building a good plan but then still iterating many many times over things that need to be fixed and tweaked until the feature can be called done. Bloggers: Here's how we use 3,000 parallel agents to write, test, and ship a new feature to production every 17 minutes in an 8M-LOC codebase (all agent-generated!). ... I'm doing something wrong, or other people ar…

To an extend you are likely doing something wrong. I understand that the natural instinct is to correct the output when you see your agent doing something wrong. That is not productive. The instinct should be to tweak the agent to do it right. At this point I am almost not writing any code in an enterprise code base.

> The instinct should be to tweak the agent to do it right.

I'm extremely doubtful of this. It doesn't save time to tell it "you have an error on line 19", because that's (often) just as much work as fixing the error. Likewise, saying "be careful and don't make mistakes" is not going to achieve anything. So how can you possibly tweak the agent to "do it right" reliably without human intervention? That's not even a solved problem for working with _humans_ who don't have the context window limitations, let alone an LLM that deletes everything past 30k tokens.

Post reply on HN