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

111–120 of 184 posts

Re: Less human AI agents, please

#111

Post by esafak »

kamaal wrote: post #72
comrade1234 wrote: post #59

Earlier quoted context omitted.

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.

The LLM only has to parse the request and farm out execution to the LSP. It saves you from having to find the function definition.

Re: Less human AI agents, please

#112

Post by BigTTYGothGF »

kamaal wrote: post #72
comrade1234 wrote: post #59

Earlier quoted context omitted.

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.

> But if a Semi is all you have

Seems like a pretty lousy work situation when you have LLMs but no decent IDE.

> the opposite is not true.

You can't ("shouldn't") take a semi on a sidewalk or down a narrow alley.

Re: Less human AI agents, please

#113

Post by PaulDavisThe1st »

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.

Works fine in algol-like languages (C, C++ for a start) by just changing the function prototype and finding all instances from the compiler errors, using your compiler as the AST explorer ...

Re: Less human AI agents, please

#114

Post by mikestorrent »

unshavedyak wrote: post #100
pavel_lishin wrote: post #83

Earlier quoted context omitted.

I think about half the IDEs I've ever used just had this as a feature. Right-click on function, click on "change signature", wait a few seconds, verify with `git diff`.

I actually still like LLMs for this. I use rust LSP (rust analyzer) and it supports this, but LLMs will additionally go through and reword all of the documentation, doc links, comments, var names in other funcs in one go, etc. Are they perfect? Far from it. But it's more comprehensive. Additionally simple refactors like this are insanely fast to review and so it's really easy to spot a bad change or etc. Plus i'm in…

Shouldn't the LLM have some tool that gives it AST access, LSP access, and the equiv of sed/grep/awk? It doesn't necessarily need to read every file and do the change "by hand".

Re: Less human AI agents, please

#115

Post by monknomo »

nialse wrote: post #66
Animats wrote: post #29

Earlier quoted context omitted.

It's inherent in the way LLMs are built, from human-written texts, that they mimic humans. They have to. They're not solving problems from first principles.

Maybe we should change that? Of course symbolic AI was the holy grail until statistical AI came in and swept the floor. Maybe something else though.

I have the unformed idea that providing a structured interface for the human user overtop the chat interface for the ai, so that the human is not chatting back and forth, could be effective? At least for things that have a structure

Re: Less human AI agents, please

#116

Post by zzzeek »

hausrat wrote: post #30

This has very little to do with someone making the LLM too human but rather a core limitation of the transformer architecture itself. Fundamentally, the model has no notion of what is normal and what is exceptional, its only window into reality is its training data and your added prompt. From the perspective of the model your prompt and its token vector is super small compared to the semantic vectors it has generated…

the best thing it could do, and once in awhile it does, is say, "hey that's really not a great way to do this and I'm not sure I could really make that work"

ive had very long sessions with LLMs that obviously didnt know how to do something where i keep trying to get it to stop going in circles, but these days I have become attuned to noticing the "it's going in circles" pattern quickly, which is basically how it communicates "sorry I dont really know how to do that".

Re: Less human AI agents, please

#117

Post by SpicyLemonZest »

rolph wrote: post #107
SpicyLemonZest wrote: post #99

Earlier quoted context omitted.

Ehhhhh, "problem" is a strong word. Sometimes you're throwing out a lot of signal if you don't let the coding agent tell you it thinks your task is a bad idea. I got a PR once attempting to copy half of our production interface because the author successfully convinced Claude his ill-formed requirements had to be achieved no matter what.

there is no use for an automated system that "argues" with your commands. if i ask it to advise me, thats one thing, but if i command it to perform, nothing short of obedience will suffice.

I just explained the use I have for it. If you think that my use case is wrong or misunderstood in some way, I'd love to hear it. If your response is just "no", I guess I'm not sure how to engage with that.

Re: Less human AI agents, please

#118

Post by zzzeek »

philipwhiuk wrote: post #84
zingar wrote: post #37

Earlier quoted context omitted.

Fascinating. This is invisible to me, what anthropomorphising did you notice that stood out?

From the first sentence > I asked an AI agent to solve a programming problem You're not asking it to solve anything. You provide a prompt and it does autocomplete. The only reason it doesn't run forever is that one of the generated tokens is interpreted as 'done'.

Ceci n'est pas une pipe

Re: Less human AI agents, please

#119

Post by zzzeek »

SpicyLemonZest wrote: post #101
philipwhiuk wrote: post #84

Earlier quoted context omitted.

From the first sentence > I asked an AI agent to solve a programming problem You're not asking it to solve anything. You provide a prompt and it does autocomplete. The only reason it doesn't run forever is that one of the generated tokens is interpreted as 'done'.

I just don't think that's correct. When I ask Claude to solve something for me, it takes a number of actions on my computer which are neither writing text nor interpreting the done token. It executes the build, debugs tests, et cetera. Sometimes it spawns mini-mes when it thinks that would be helpful! I think saying this is all "autocomplete" is a category error, like saying that you shouldn't talk about clicking but…

yup, or "I played a first person shooter and shot lots of bad guys"

wrong! pushed buttons on your playstation in response to graphical simulations, duh

Re: Less human AI agents, please

#120

Post by happygoose »

SpicyLemonZest wrote: post #101
philipwhiuk wrote: post #84

Earlier quoted context omitted.

From the first sentence > I asked an AI agent to solve a programming problem You're not asking it to solve anything. You provide a prompt and it does autocomplete. The only reason it doesn't run forever is that one of the generated tokens is interpreted as 'done'.

I just don't think that's correct. When I ask Claude to solve something for me, it takes a number of actions on my computer which are neither writing text nor interpreting the done token. It executes the build, debugs tests, et cetera. Sometimes it spawns mini-mes when it thinks that would be helpful! I think saying this is all "autocomplete" is a category error, like saying that you shouldn't talk about clicking but…

technically, it does all that by outputting text, like `run_shell_command("cargo build")` as part of its response. But you could easily say similar things about humans.

To me, "autocomplete" seems like it describes the purpose of a system more than how it functions, and these agents clearly aren't designed to autocomplete text to make typing on a phone keyboard a bit faster.

I feel like people compare it to "autocomplete" because autocomplete seems like a trivial, small, mundane thing, and they're trying to make the LLMs feel less impressive. It's a rhetorical trick that is very overused at this point.

Post reply on HN