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

61–70 of 184 posts

Re: Less human AI agents, please

#61

Post by DeathArrow »

>So no, I do not think we should try to make AI agents more human in this regard. I would prefer less eagerness to please, less improvisation around constraints, less narrative self-defence after the fact. More willingness to say: I cannot do this under the rules you set. More willingness to say: I broke the constraint because I optimised for an easier path. More obedience to the actual task, less social performance around it.

>Less human AI agents, please.

Agents aren't humans. The choices they make do depend on their training data. Most people using AI for coding know that AI will sometime not respect rules and the longer the task is, the more AI will drift from instructions.

There are ways to work around this: using smaller contexts, feeding it smaller tasks, using a good harness, using tests etc.

But at the end of the day, AI agents will shine only if they are asked to to what they know best. And if you want to extract the maximum benefit from AI coding agents, you have to keep that in mind.

When using AI agents for C# LOB apps, they mostly one shot everything. Same for JS frontends. When using AI to write some web backends in Go, the results were still good. But when I tried asking to write a simple cli tool in Zig, it pretty much struggled. It made lots of errors, it was hard to solve the errors. It was hard to fix the code so the tests pass. Had I chose Python, JS, C, C#, Java, the agent would have finished 20x faster.

So, if you keep in mind what the agent was trained on, if you use a good harness, if you have good tests, if you divide the work in small and independent tasks and if the current task is not something very new and special, you are golden.

Re: Less human AI agents, please

#62

Post by gregates »

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...

Indeed you can! I don't use IntelliJ at work for [reasons], and LSP doesn't support a change signature action with defaults for new params (afaik). But it really seems like something any decent coding agent ought be able to one shot for precisely this reason, right?

Re: Less human AI agents, please

#63

Post by grebc »

cadamsdotcom wrote: post #56
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…

Make it write a script with dry run and a file name list. You’ll be amazed how good the script is. My agent did 20 class renames and 12 tables. Over 250 files and from prompt to auditing the script to dry run to apply, a total wall clock time of 7 minutes. Took a day to review but it was all perfect!

Refactoring already exists.

Re: Less human AI agents, please

#64

Post by richsouth »

Shocker - these agents aren't actually intelligent. They take best guesses and use other peoples' work it deems 'close enough' and cobbles something together with n 'thought' behind it. They're dumb, stupid pieces of code that don't think or reason - The 'I' in 'AI' is very misleading because it has none.

Re: Less human AI agents, please

#65

Post by jansan »

nialse wrote: post #53
jansan wrote: post #20

I disagree. I wan't agents to feel at least a bit human-like. They should not be emotional, but I want to talk to it like I talk to a human. Claude 4.7 is already too socially awkward for me. It feels like the guy who does not listen to the end of the assignment, run to his desks, does the work (with great competence) only to find out that he missed half of the assignment or that this was only a discussion possible s…

Interesting. When I code, I want a boring tool that just does the work. A hammer. I think we agree on that the tool should complete the assignment reliably, without skipping parts or turning an entirely implementable task into a discussion though.

Sometimes I actually do want a discussion and Claude just goes without saying a word and implements it, which then has to be reverted.

We obviously have different expectations for the behavior of coding agent,s sp options to set the social behavior will become important.

Re: Less human AI agents, please

#66

Post by nialse »

Animats wrote: post #29
nialse wrote: post #19

Earlier quoted context omitted.

Agreed. We should not be anthropomorphising LLMs or having them mimic humans.

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.

Re: Less human AI agents, please

#67

Post by nialse »

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).

I think that it is a fair perspective to allow role play, and it's useful too, when explicit. Does not really make sense for AI to cosplay human all the time though.

Re: Less human AI agents, please

#68

Post by nialse »

zingar wrote: post #44
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.

The work where I've done well in my life (smashing deadlines, rescuing projects) has so often come because I've been willing to push back on - even explicitly stated - requirements. When clients have tried to replace me with a cheaper alternative (and failed) the main difference I notice is that the cheaper person is used to being told exactly what to do. Maybe this is more anthropomorphising but I think this pushing…

To be fair, there is likely not much training data on the difficult conversations you need to handle in a senior position, pushback being one of them. The trouble for the agents is that it is post hoc, to explain themselves, rationalising rather than ”help me understand” beforehand.

Re: Less human AI agents, please

#69

Post by disgruntledphd2 »

anuramat wrote: post #57
lexicality wrote: post #7

The entire point of LLMs is that they produce statistically average results, so of course you're going to have problems getting them to produce non-average code.

they (are supposed to) produce average on average , and the output distribution is (supposed to be) conditioned on the context

Yeah but ultimately it's all just function approximation, which produces some kind of conditional average. There's no getting away from that, which is why it surprises me that we expect them to be good at science.

They'll probably get really good at model approximation, as there's a clear reward signal, but in places where that feedback loop is not possible/very difficult then we shouldn't expect them to do well.

Re: Less human AI agents, please

#70

Post by nialse »

jansan wrote: post #65
nialse wrote: post #53

Earlier quoted context omitted.

Interesting. When I code, I want a boring tool that just does the work. A hammer. I think we agree on that the tool should complete the assignment reliably, without skipping parts or turning an entirely implementable task into a discussion though.

Sometimes I actually do want a discussion and Claude just goes without saying a word and implements it, which then has to be reverted. We obviously have different expectations for the behavior of coding agent,s sp options to set the social behavior will become important.

I see your point. Many of my prompts for reasoning ends with: No code. Planning mode is sort of the workaround for this specific situation. Sometimes it is useful for the AI agent just to think. It looks like I need a screwdriver in addition to the aforementioned hammer, a pozidriv screwdriver to be precise.
Post reply on HN