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

31–40 of 184 posts

Re: Less human AI agents, please

#31

Post by fennecbutt »

zingar wrote: post #28

I think the author is looking for something that doesn't exist (yet?). I don't think there's an agent in existence that can handle a list of 128 tasks exactly specified in one session. You need multiple sessions with clear context to get exact results. Ralph loops, Gastown, taskmaster etc are built for this, and they almost entirely exist to correct drift like this over a longer term. The agent-makers and models are…

Not with tools + supporting (traditional) code.

Just as a human would use a task list app or a notepad to keep track of which tasks need to be done so can a model.

You can even have a mechanism for it to look at each task with a "clear head" (empty context) with the ability to "remember" previous task execution (via embedding the reasoning/output) in case parts were useful.

Re: Less human AI agents, please

#32

Post by fennecbutt »

nialse wrote: post #26
plastic041 wrote: post #18

> There was only one small issue: it was written in the programming language and with the library it had been told not to use. This was not hidden from it. It had been documented clearly, repeatedly, and in detail. What a human thing to do. "Ignoring" instructions is not human thing. It's a bad LLM thing. Or just LLM thing.

It's not necessarily "ignoring" instructions, it's the ironic effect of mentioning something not to focus on, which produces focus on said thing. The classic version is: "For the next minute, try not to think about a pink elephant. You can think about anything else you like, just not a pink elephant." https://en.wikipedia.org/wiki/Ironic_process_theory

Yes exactly. But for llms it's more that it's not really "thinking" about what it's saying per se, it's that it's predicting next token. Sure, in a super fancy way but still predicting next token. Context poisoning is real

Re: Less human AI agents, please

#33

Post by zingar »

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…

> Maybe we should just commit the signature change with a TODO

I'm fascinated that so many folks report this, I've literally never seen it in daily CC use. I can only guess that my habitually starting a new session and getting it to plan-document before action ("make a file listing all call sites"; "look at refactoring.md and implement") makes it clear when it's time for exploration vs when it's time for action (i.e. when exploring and not acting would be failing).

Re: Less human AI agents, please

#35

Post by zingar »

fennecbutt wrote: post #31
zingar wrote: post #28

I think the author is looking for something that doesn't exist (yet?). I don't think there's an agent in existence that can handle a list of 128 tasks exactly specified in one session. You need multiple sessions with clear context to get exact results. Ralph loops, Gastown, taskmaster etc are built for this, and they almost entirely exist to correct drift like this over a longer term. The agent-makers and models are…

Not with tools + supporting (traditional) code. Just as a human would use a task list app or a notepad to keep track of which tasks need to be done so can a model. You can even have a mechanism for it to look at each task with a "clear head" (empty context) with the ability to "remember" previous task execution (via embedding the reasoning/output) in case parts were useful.

The article makes it seem like the author expected this without emptying context in between, which does not yet exist (actually I'm behind on playing with Opus 4.7, the Anthropic claim seems to be that longer sessions are ok now - would be interested to hear results from anyone who has).

Re: Less human AI agents, please

#36

Post by nialse »

zingar wrote: post #28

I think the author is looking for something that doesn't exist (yet?). I don't think there's an agent in existence that can handle a list of 128 tasks exactly specified in one session. You need multiple sessions with clear context to get exact results. Ralph loops, Gastown, taskmaster etc are built for this, and they almost entirely exist to correct drift like this over a longer term. The agent-makers and models are…

Agreed. I am asking for something beyond the current state of the art. My guess is that stronger RL on the model side, together with better harness support, will eventually make it possible. However, it's the part about framing the failure to do complete a task as a communication mishap that really makes me go awry.

Re: Less human AI agents, please

#37

Post by zingar »

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?

Re: Less human AI agents, please

#38

Post by chillfox »

gregates wrote: post #27
grebc wrote: post #24

Earlier quoted context omitted.

If it’s a compiled language, just change the definition and try to compile.

Indeed! You would think it would have some kind of sense that a commit that obviously won't compile is bad! You would think. It would be one thing if it was like, ok, we'll temporarily commit the signature change, do some related thing, then come back and fix all the call sites, and squash before merging. But that is not the proposal. The plan it proposes is literally to make what it has identified as the minimal cha…

Pretty sure it’s a harness or system prompt issue.

I have never seen those “minimal change” issues when using zed, but have seen them in claude code and aider. Been using sonnet/opus high thinking with the api in all the agents I have tested/used.

Re: Less human AI agents, please

#39

Post by chrisjj »

prymitive wrote: post #25
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…

That’s my daily experience too. There are a few more behaviours that really annoys me, like: - it breaks my code, tests start to fail and it instantly says “these are all pre existing failures” and moves on like nothing happened - or it wants to run some a command, I click the “nope” button and it just outputs “the user didn’t approve my command, I need to try again” and I need to click “nope” 10 more times or yell a…

> 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".

Re: Less human AI agents, please

#40

Post by solumunus »

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 need to use explicit instructions like "make a TODO list of all call sites and use sub agents to fix them all".
Post reply on HN