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

Less human AI agents, please

nial.se

Post reply on HN
Print view View original

71–80 of 184 posts

Re: Less human AI agents, please

#71

Post by chrisjj »

nialse wrote: post #60
chrisjj wrote: post #39

Earlier quoted context omitted.

> it breaks my code, tests start to fail and it instantly says “these are all pre existing failures” and moves on like nothing happened Reminds us of the most important button the "AI" has, over the similarly bad human employee. 'X' Until, of course, we pass resposibility for that button to an "AI".

The other day Codex on Mac gained the ability to control the UI. Will it close itself if instructed though? Maybe test that and make a benchmark. Closebench.

My point was more: will it stop the user closing it?

Re: Less human AI agents, please

#72

Post by kamaal »

comrade1234 wrote: post #59
gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

You can do that in IntelliJ in about 15 seconds and no tokens...

Using a LLM for these tasks really is somewhat like using a Semi to shuttle your home groceries. Absolutely unnecessary, and can be done via a scooter. But if a Semi is all you have you use it for everything. So here we are.

The real deal is, while a Semi can do all the things you can do with a scooter, the opposite is not true.

Re: Less human AI agents, please

#73

Post by matthiasrsl »

NitpickLawyer wrote: post #9
mentalgear wrote: post #6

Yes, LLMs should not be allowed to use "I" or indicate they have emotions or are human-adjacent (unless explicit role play).

Why, though? Just because some people would find it odd? Who cares? Trying to limit / disallow something seems to be hurting the overall accuracy of models. And it makes sense if you think about it. Most of our long-horizon content is in the form of novels and above. If you're trying to clamp the machine to machine speak you'll lose all those learnings. Hero starts with a problem, hero works the problem, hero reaches…

Is it? I don't think most of the content LLM are trained on is written in the first person. Wikipedia / news articles / other information articles don't aren't written in the first person. Most novels, or at least a substantial portion of it are not written in the first person.

LLM write in the first person because they have been specifically been finetuned for a chat task, it's not a fundamental feature of language models that would have to be specifically disallowed

Re: Less human AI agents, please

#74

Post by solumunus »

gregates wrote: post #55
solumunus wrote: post #42

Earlier quoted context omitted.

On my compiled language projects I have a stop hook that compiles after every iteration. The agent literally cannot stop working until compilation succeeds.

In the case I described no code changes have been made yet. It's still just planning what to do. It's true that I could accept the plan and hope that it will realize that it can't commit a change that doesn't compile on its own, later. I might even have some reason to think that's true, such as your stop hook, or a "memory" it wrote down before after I told it to never ever commit a change that doesn't compile, in al…

I think your expectations are too high. Just understand the limitations and go with the flow.

Re: Less human AI agents, please

#75

Post by SoftTalker »

gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

> changing a commonly used fn to take a locale parameter

I have to ask, is this the sort of thing people use agents/AI for?

Because I'd probably reach for sed or awk.

Re: Less human AI agents, please

#76

Post by bob1029 »

gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

> I found 67 call sites. This is a pretty substantial change. Maybe we should just commit the signature change with a TODO to update all the call sites, what do you think?

I think some of this is a problem in the agent's design. I've got a custom harness around GPT5.4 and I don't let my agent do any tool calling on the user's conversation. The root conversation acts as a gatekeeper and fairly reliably pushes crap responses like this back down into the stack with "Ok great! Start working on items 1-20", etc.

Re: Less human AI agents, please

#77

Post by jxf »

SoftTalker wrote: post #75
gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

> changing a commonly used fn to take a locale parameter I have to ask, is this the sort of thing people use agents/AI for? Because I'd probably reach for sed or awk.

It's not always amenable to grepping. But this is a great use case for AST searches, and is part of the reason that LSP tools should really be better integrated with agents.

Re: Less human AI agents, please

#78

Post by CPLX »

gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

I've have a different version of the same thing. My pet peeve is that it constantly interprets questions as instructions.

For example, it does a bunch of stuff, and I look at it and I say, "Did we already decide to do [different approach]" And then it runs around and says, "Oh yeah," and then it does a thousand more steps and undoes does what it just did and gets itself into a tangle.

Meanwhile, I asked it a question. The proper response would be to answer the question. I just want to know the answer.

I had it right. That behavior into a core memory, and it seems to have improved for what it's worth.

Re: Less human AI agents, please

#79

Post by scottlamb »

SoftTalker wrote: post #75
gregates wrote: post #15

The version of this I encounter literally every day is: I ask my coding agent to do some tedious, extremely well-specified refactor, such as (to give a concrete real life example) changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware. I am very clear — we are not actually changing any behavior, just the fn signature. In fact, at all call sites, I want it to specify a def…

> changing a commonly used fn to take a locale parameter I have to ask, is this the sort of thing people use agents/AI for? Because I'd probably reach for sed or awk.

In general, yes, I might use an LLM for a tedious refactor. In this case I might try https://github.com/ast-grep/ast-grep> though.

Re: Less human AI agents, please

#80

Post by philipwhiuk »

jxf wrote: post #77
SoftTalker wrote: post #75

Earlier quoted context omitted.

> changing a commonly used fn to take a locale parameter I have to ask, is this the sort of thing people use agents/AI for? Because I'd probably reach for sed or awk.

It's not always amenable to grepping. But this is a great use case for AST searches, and is part of the reason that LSP tools should really be better integrated with agents.

Ah yes, don't fix the agents, fix the tools.

What a ridiculously backwards approach.

We were supposed to get agents who could use human tooling. Instead we are apparently told to write interfaces for this stumbling expensive mess to use.

Maybe, just maybe, if the human can know to, and use, the AST tool fine, the problem is not the tool but the agent.

Post reply on HN