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

81–90 of 184 posts

Re: Less human AI agents, please

#81

Post by saalweachter »

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.

> while a Semi can do all the things you can do with a scooter

You may be able to lane split in a semi, but it also has excessive environmental impact.

Re: Less human AI agents, please

#82

Post by philipwhiuk »

chrisjj wrote: post #41
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…

> How should it decide whether your prompt is actually interesting novel exploration of an unknown concept or just complete bogus? It shouldn't. It should just do what it is told.

Remember that all it's actually 'doing' is predicting more text.

Re: Less human AI agents, please

#83

Post by pavel_lishin »

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.

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`.

Re: Less human AI agents, please

#84

Post by philipwhiuk »

zingar wrote: post #37
raincole wrote: post #5

I know anthropomorphizing LLMs has been normalized, but holy shit . I hope the language in this article is intentionally chosen for a dramatic effect.

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'.

Re: Less human AI agents, please

#85

Post by Arch485 »

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.

Or the "find all references" feature almost every code editor has...

Re: Less human AI agents, please

#86

Post by ep103 »

pavel_lishin wrote: post #83
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.

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`.

yeah, and this has the advantage of both being deterministic, and only updating things that are actually linked as opposed to also accidentally updating naming collisions

Re: Less human AI agents, please

#87

Post by larrytheworm »

js8 wrote: post #12

A very human thing to do is - not to tell us which model has failed like this! They are not all alike, some are, what I observe, order of magnitude better at this kind of stuff than others. I believe how "neurotypical" (for the lack of a better word) you want model to be is a design choice. (But I also believe model traits such as sycophancy, some hallucinations or moral transgressions can be a side effect of trainin…

[dead]

Re: Less human AI agents, please

#88

Post by winddude »

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 never hit that one, do you have a lot of `ToDo`s in your code comments?

Re: Less human AI agents, please

#89

Post by mempko »

This is a harness problem just as much as it is a model problem. I've been working on Abject (https://abject.world) and the project has agents. I took a different approach than most agent frameworks via the goal system, but still I was surprised with some of the stuff the agents generated even with guardrails. It actually helped harden the system!
Post reply on HN