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

Learnings from building AI agents

cubic.dev

Post reply on HN
Print view View original

31–40 of 70 posts

Re: Learnings from building AI agents

#31

Post by asdev »

h1fra wrote: post #8

what I saw using 5-6 tools like this: - PR description is never useful they barely summarize the file changes - 90% of comments are wrong or irrelevant wether it's because it's missing context, missing tribal knowledge, missing code quality rules or wrongly interpret the code change - 5-10% of the time it actually spots something Not entirely sure it's worth the noise

the code reviews can't be effective because the LLM does not have the tribal knowledge and product context of the change. it's just reading the code at face value

Re: Learnings from building AI agents

#32

Post by Oras »

The problem is that, regardless of how you try to use "micro-agents " as a marketing term, LLMs are instructed to return a result.

They will always try to come up with something.

The example provided was a poor one. The comment from LLM was solid. Why would you comment out a step in the pipeline instead of just deleting it? I would comment the same in a PR.

Re: Learnings from building AI agents

#33

Post by disgruntledphd2 »

nico wrote: post #23
curiousgal wrote: post #14

> Encouraged structured thinking by forcing the AI to justify its findings first, significantly reducing arbitrary conclusions. Ah yes, because we know very well that the current generation of AI models reasons and draws conclusions based on logic and understanding... This is the true face palm.

Humans work pretty much the same way Several studies have shown that we first make the decision and then we reason about it to justify it In that sense, we are not much more rational than an LLM

Humans have a lot more introspection capabilities than any current LLM.

Re: Learnings from building AI agents

#34

Post by elzbardico »

Funny thing is the structured output in the last example.

``` { "reasoning": "`cfg` can be nil on line 42; dereferenced without check on line 47", "finding": "Possible nil‑pointer dereference", "confidence": 0.81 } ```

You know the confidence value is completely bogus, don't you?

Re: Learnings from building AI agents

#35

Post by elzbardico »

curiousgal wrote: post #14

> Encouraged structured thinking by forcing the AI to justify its findings first, significantly reducing arbitrary conclusions. Ah yes, because we know very well that the current generation of AI models reasons and draws conclusions based on logic and understanding... This is the true face palm.

The "confidence" field in the structured output was what really baffled me.

Re: Learnings from building AI agents

#36

Post by alganet »

nico wrote: post #23
curiousgal wrote: post #14

> Encouraged structured thinking by forcing the AI to justify its findings first, significantly reducing arbitrary conclusions. Ah yes, because we know very well that the current generation of AI models reasons and draws conclusions based on logic and understanding... This is the true face palm.

Humans work pretty much the same way Several studies have shown that we first make the decision and then we reason about it to justify it In that sense, we are not much more rational than an LLM

> Several studies

Please, cite those studies. I want to read them.

Re: Learnings from building AI agents

#37

Post by SparkyMcUnicorn »

Oras wrote: post #32

The problem is that, regardless of how you try to use "micro-agents " as a marketing term, LLMs are instructed to return a result. They will always try to come up with something. The example provided was a poor one. The comment from LLM was solid. Why would you comment out a step in the pipeline instead of just deleting it? I would comment the same in a PR.

I've found that giving agents an "opt out" works pretty well.

For structured outputs, making fields optional isn't usually enough. Providing an additional field for it to dump some output, along with a description for how/when it should be used, covers several issues around this problem.

I'm not claiming this would solve the specific issues discussed in the post. Just a potentially helpful tip for others out there.

Re: Learnings from building AI agents

#38

Post by wrs »

AndrewKemendo wrote: post #26
mattas wrote: post #20

"After extensive trial-and-error..." IMO, this is the difference between building deterministic software and non-deterministic software (like an AI agent). It often boils down to randomly making tweaks and evaluating the outcome of those tweaks.

Otherwise known as science 1:Observation 2:Hypothesis 3:test 4:GOTO:1 This is every thing ever built ever What is the problem exactly?

For one thing, what you learned can stop working when you switch to a new model, or just a newer version of the “same” model.

Re: Learnings from building AI agents

#39

Post by jstummbillig »

The multi agent thing with different roles is so obviously not a great concept, that I am very hesitant to build towards it, even thought it seems to win out right now. We want a AI that internally does what it needs to do to solve a problem, given a good enough problem description, tools and context. I really do not want to have to worry about breaking up tasks into chunks that are smaller than what I could handle myself, and I really hope that that in the near future this will go away.

Re: Learnings from building AI agents

#40

Post by sharkjacobs »

elzbardico wrote: post #34

Funny thing is the structured output in the last example. ``` { "reasoning": "`cfg` can be nil on line 42; dereferenced without check on line 47", "finding": "Possible nil‑pointer dereference", "confidence": 0.81 } ``` You know the confidence value is completely bogus, don't you?

Do you mean that there is no correlation between confidence and false positives or other errors?
Post reply on HN