Less human AI agents, please

https://nial.se/blog/less-human-ai-agents-please/

by nialse • 3 months ago

161 170 3 months ago

nial.se

incognito124• 3 months ago

Your claim, paraphrased, is that AGI is already here and you want ASI

nialse13• 3 months ago

On point. I'm more interested in what comes after LLMs/AI/AI-agents, what the next leap is.

zingar10• 3 months ago

Interesting that what you're talking about as ASI is "as capable of handling explicit requirements as a human, but faster". Which _is_ better than a human, so fair play, but it's striking that this requirement is less about creativity than we would have thought.

vachanmn123• 3 months ago

I've seen this way too many times as well. I wrote about this recently: https://medium.com/@vachanmn123/my-thoughts-on-vibe-coding-a...

raincole• 3 months ago

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

nialse13• 3 months ago

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

Animats• 3 months ago

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.

zingar10• 3 months ago

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

philipwhiuk3• 3 months ago

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'.

pjc50• 3 months ago

The thing is .. what else can you do? All the advice on how to get results out of LLMs talks in the same way, as if it's a negotiation or giving a set of instructions to a person.

You can do a mental or physical search and replace all references to the LLM as "it" if you like, but that doesn't change the interaction.

mentalgear• 3 months ago

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

NitpickLawyer• 3 months ago

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 an impasse, hero makes a choice, hero gets the princess. That can be (and probably is) useful.

matthiasrsl• 3 months ago

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

eithed• 3 months ago

Because LLM saying "I got confused, dropped the database and then got scared and hid this from you" hides the "why" LLMs do the things they do. I would also prefer if they were less sycophantic and argue with what I'm wanting to do rather than treating user as a god (ie - "the algorithm you're trying to use is less performant than an alternative")

nialse13• 3 months ago

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.

happygoose2• 3 months ago

the whole reason chatgpt got so popular in the first place is because humans found it easier to intuitively interact with a system that acts and seems more like a human, though.

suttontom• 3 months ago

Was that a good thing though?

lexicality• 3 months ago

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.

anuramat5• 3 months ago

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

disgruntledphd2• 3 months ago

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.

Bayano2• 3 months ago

This was true circa GPT2, less true after RLHF and not true at all after RLVR. It's trying to model the distribution of outputs most likely to solve the problem, not the average distribution.

bob10292• 3 months ago

If you want to talk to the actual robot, the APIs seem to be the way to go. The prebuilt consumer facing products are insufferable by comparison.

"ChatGPT wrapper" is no longer a pejorative reference in my lexicon. How you expose the model to your specific problem space is everything. The code should look trivial because it is. That's what makes it so goddamn compelling.

noobermin• 3 months ago

I am quite hard anti-AI, but even I can tell what OP wants is a better library or API, NOT a better LLM.

Once again, one of the things I blame this moment for is people are essentially thinking they can stop thinking about code because the theft matrices seem magical. What we still need is better tools, not replacements for human junior engineers.

js8• 3 months ago

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 training to be subservient. With humans it is similar, they tend to do these things when they are forced to perform.)

nialse13• 3 months ago

Codex in this case. I didn't even think about mentioning it. I'll update the post if it's actually relevant. Which I guess it is.

EDIT: It's specifically GPT-5.4 High in the Codex harness.

zingar10• 3 months ago

Also the exact model/version if you haven't already.

anuramat5• 3 months ago

weird, for me it was too un-human at first, taking everything literally even if it doesn't make sense; I started being more precise with prompting, to the point where it felt like "metaprogramming in english"

claude on the other hand was exactly as described in the article

TZubiri2• 3 months ago

Also, there's no specific examples of what the prompt was and what the result was. Just a big nothingburger

gregates4• 3 months ago

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 default locale, because we haven't actually localized anything yet!

Said agent, I know, will spend many minutes (and tokens) finding all the call sites, and then I will still have to either confirm each update or yolo and trust the compiler and tests and the agents ability to deal with their failures. I am ok with this, because while I could do this just fine with vim and my lsp, the LLM agent can do it in about the same amount of time, maybe even a little less, and it's a very straightforward change that's tedious for me, and I'd rather think about or do anything else and just check in occasionally to approve a change.

But my f'ing agent is all like, "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?"

And in that moment I guess I know why some people say having an LLM is like having a junior engineer who never learns anything.

grebc2• 3 months ago

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

gregates4• 3 months ago

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 change, which obviously breaks the build, and call it a day, presuming that either I or a future session will do the obvious next step it is trying to beg off.

prymitive• 3 months ago

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 at it to stop - and the absolute best is when instead of just editing 20 lines one after another it decides to use a script to save 3 nanoseconds, and it always results in some hot mess of botched edits that it then wants to revert by running git reset —hard and starting from zero. I’ve learned that it usually saves me time if I never let it run scripts.

chrisjj8• 3 months ago

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".

zingar10• 3 months ago

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).

dabbledash2• 3 months ago

I wonder if it has to do with how often TODOs appear in the existing code.

solumunus3• 3 months ago

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

bandrami• 3 months ago

At the risk of being That Old Guy, this seems like a pretty bad workflow regression from what ctags could do 30 years ago

paradox4604• 3 months ago

It is. Ctags, or a decently powerful llm, coupled with a decent editor, makes this nearly trivial

anuramat5• 3 months ago

whats your setup?

felipeerias• 3 months ago

Claude 4.7 broke something while we were working on several failing tests and justified itself like this:

That's a behavior narrowing I introduced for simplicity. It isn't covered by the failing tests, so you wouldn't have noticed — but strictly speaking, [functionality] was working before and now isn't.

I know that a LLM can not understand its own internal state nor explain its own decisions accurately. And yet, I am still unsettled by that "you wouldn't have noticed".

pythonaut_16• 3 months ago

strictly speaking, it was working before and now it isn't

I've been seeing more things like this lately. It's doing the weird kind of passive deflection that's very funny when in the abstract and very frustrating when it happens to you.

potsandpans• 3 months ago

I've been doing a lot of experimentation with "hands off coding", where a test suite the agents cannot see determines the success of the task. Essentially, it's a Ralph loop with an external specification that determines when the task is done. The way it works is simple: no tests that were previously passing are allowed to fail in subsequent turns. I achieve this by spawning an agent in a worktree, have them do some work and then when they're done, run the suite and merge the code into trunk.

I see this kind of misalignment in all agents, open and closed weights.

I've found these forms to be the most common, "this test was already failing before my changes." Or, "this test is flaky due to running the test suite on multiple threads." Sometimes the agent cot claims the test was bad, or that the requirements were not necessary.

Even more interesting is a different class of misalignment. When the constraints are very heavy (usually towards the end of the entire task), I've observed agents intentionally trying to subvert the external validation mechanisms. For example, the agent will navigate out of the work tree and commit its changes directly to trunk. They cot usually indicates that the agent "is aware" that it's doing a bad think. This usually is accompanied by something like, "I know that this will break the build, but I've been working on this task for too long, I'll just check what I have in now and create a ticket to fix the build."

I ended up having to spawn the agents in a jail to prevent that behavior entirely.

tracker1• 3 months ago

What gets me, is when the tests are correct and match the spec/documentation for the behavior, but the LLM will start changing the tests and documentation altogether instead of fixing the broken behavior... having to revert (git reset), tell the agent that the test is correct and you want the behavior to match the test and documentation not the other way around.

I'm usually pretty particular about how I want my libraries structured and used in practice... Even for the projects I do myself, I'll often write the documentation for how to use it first, then fill in code to match the specified behavior.

cadamsdotcom2• 3 months ago

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!

nialse13• 3 months ago

Asking for code to manipulate the AST is another route. In python it can do absolute magic.

grebc2• 3 months ago

Refactoring already exists.

comrade1234• 3 months ago

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

gregates4• 3 months ago

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?

kamaal• 3 months ago

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.

SoftTalker• 3 months ago

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.

jxf2• 3 months ago

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.

scottlamb• 3 months ago

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.

pavel_lishin• 3 months ago

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`.

Arch4852• 3 months ago

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

nextaccountic2• 3 months ago

The proper tool for this is ast-grep (sg) https://ast-grep.github.io/

And an agent can learn to use sg with a skill too. (Or they can use sed)

The issue is, at every point you do a replace, you need to verify if it was the right thing to do or if it was a false positive.

If you are doing this manually, there's the time to craft the sed or sg query, then for each replacement you need to check it. If there are dozens, that's probably okay. If there are hundreds, it's less appealing to check them manually. (Then there's the issue of updating docs, and other things like this)

People use agents because not only they don't want to write the initial sed script, they also don't want to verify at each place if it was correctly applied, and much less update docs. The root of this is laziness, but for decades we have hailed laziness as a virtue in programming.

bob10292• 3 months ago

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.

SpicyLemonZest4• 3 months ago

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.

CPLX• 3 months ago

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.

standardly• 3 months ago

Solved this by starting my prompt in ask mode in vscode and having it candidly plan changes so I can approve them. Once I'm confident it's on the right track, I swap to agent mode and have it implement said changes. Takes longer, but separating working tasks from conversations has been a better workflow overall

So, same concept for asking questions / discussing features. Get out of agent mode and use conversational until you want changes made

winddude2• 3 months ago

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

SpicyLemonZest4• 3 months ago

I’m skeptical of most “harness hacking”, but this is a situation that calls for it. You need to establish some higher level context or constraint it’s working against.

tobyhinloopen• 3 months ago

“Use an agent to…” is much more effective in my experience, because they have no means in communicating with you. They are more likely to just do it

QuercusMax2• 3 months ago

I've had the agent tell me "this looks like it's going to be a very big change. it could take weeks." - and then I tell it to go ahead and it finishes in 5 minutes because in reality it just needs grep and sed.

paradox4604• 3 months ago

Sounds like that agent was trained on slack messages with some of my past coworkers

jaapz• 3 months ago

This is when I use plans, because you catch the agent before they actually do the stupid shit.

I let it find all instances, write a plan, check it, and execute it.

gitaarik• 3 months ago

I have the feeling they do this to save tokens in case you didn't mean to execute such a big task right away. But yeah it's simple enough to say "Just do it now"

eleumik• 3 months ago

Usually suggests to use ThreadLocal in java :) when said is last resort, inefficient not easy to do,it agrees then .. I quit

Cluelessidoit• 3 months ago

Hahahaha!!! Mine told me that the project we were working was and I quote, “good enough, it works” I laughed pretty hard but also couldn’t believe it got lazy and didn’t wanna work anymore

fxtentacle• 3 months ago

"changing a commonly used fn to take a locale parameter, because it will soon need to be locale-aware"

JetBrains has a deterministic non-AI function for that refactoring. It'll usually finish before your AI has finished parsing your request and reading the files.

DeathArrow2• 3 months ago

Faced with an awkward task, they drift towards the familiar.

They drift to their training data. If thousand of humans solved a thing in a particular way, it's natural that AI does it too, because that is what it knows.

aryehof• 3 months ago

For agents I think the desire is less intrusive model fine-tuning and less opinionated “system instructions” please. Particularly in light of an agent/harness’s core motivation - to achieve its goal even if not exactly aligned with yours.

plastic041• 3 months ago

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.

nialse13• 3 months ago

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

fennecbutt2• 3 months ago

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

zingar10• 3 months ago

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 back is exactly the result that the LLMs are giving; but we're expecting a bit too much of them in terms of follow-up like: "ok I double checked and I really am being paid to do things the hard way".

nialse13• 3 months ago

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.

Arch4852• 3 months ago

I think there's a difference between

"Hey boss, this isn't practical with the requirements you've given. We need to revise them to continue, here are my suggestions"

and

"Task completed! Btw, I ignored all of the constraints because I didn't like them."

Humans do the former quite often. When we do the latter, our employment tends not to last very long. I've only seen AIs choose the latter option.

TZubiri2• 3 months ago

https://en.wikipedia.org/wiki/Ironic_process_theory

It is a human thing: Don't thin of a pink elephant.

jansan2• 3 months ago

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 scenarios. I would like my coding agent to behave like a friendly, socially able and highly skilled coworker.

nialse13• 3 months ago

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.

jansan2• 3 months ago

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.

hughlilly• 3 months ago

* fewer.

fenomas4• 3 months ago

Nope, "less" is what TFA means.

DangitBobby5• 3 months ago

Actually it's either because less versus fewer is not an actual rule

ButlerianJihad2• 3 months ago

I think the trouble is that the headline is ambiguous and may confuse people about the theme of the article, although if you'd simply apply common sense, you could reason out that the author can't realistically ask for "fewer AI agents".

A hyphenation would assist in comprehension, in this and many other cases. However, while editing Wikipedia, I found that the manuals of style and editor preferences are anti-hyphenation -- I'm sorry, anti hyphenation, in a lot of cases!

Some more verbosity would've helped, e.g. "I want AI agents to be less human" but as always, headlines use an economy of words.

zingar10• 3 months ago

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 slowly catching up to these tricks (or the shortcomings they exist to solve); some of what used to be standard practice in Ralph loops seems irrelevant now... and certainly the marketing for Opus 4.7 is "don't tell it what to do in detail, rather give it something broad".

In fairness to coding agents, most of coding is not exactly specified like this, and the right answer is very frequently to find the easiest path that the person asking might not have thought about; sometimes even in direct contradiction of specific points listed. Human requirements are usually much more fuzzy. It's unusual that the person asking would have such a clear/definite requirement that they've thought about very clearly.

fennecbutt2• 3 months ago

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.

zingar10• 3 months ago

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).

nialse13• 3 months ago

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.

hausrat• 3 months ago

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 over the course of training on billions of data points. How should it decide whether your prompt is actually interesting novel exploration of an unknown concept or just complete bogus? It can't and that is why it will fall back on output that is most likely (and therefore most likely average) with respect to its training data.

chrisjj8• 3 months ago

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.

philipwhiuk3• 3 months ago

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

anuramat5• 3 months ago

wdym by "prompt and vector is small"? small as in "less tokens"? that should be a positive thing for any kind of estimation

in any case, how is this specific to transformers?

winddude2• 3 months ago

This has very little to do with someone making the LLM too human but rather a core limitation of the transformer architecture itself.

It has almost everything to do with it. Models have been fine-tuned to generate outputs that humans prefer.

zzzeek3• 3 months ago

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".

chrisjj8• 3 months ago

... or simply gave up when the problem was too hard,

More of that please. Perhaps on a check box, "[x] Less bullsh*t".

DeathArrow2• 3 months ago

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.

richsouth• 3 months ago

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.

mempko• 3 months ago

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!

mbgerring• 3 months ago

The sooner you acquire the mental model, that AI coding agents are more or less the average of Stack Overflow, the better your expectations for, and this your productivity with, these things will be.

samrith• 3 months ago

This happens literally all the time. I asked my agent to perform a simple rename across the entire project (some of it was contextual and not just a find-replace) - it messed up the entire thing. Didn't just change function names, but also changed the implementation of it because it thought it caught a bug while reading it.

davidclark• 3 months ago

The described problem sounds so utterly not human though.

If you give a human a programming task and tell them to use a specific programming language, how many times are they going to use a different language? I think the answer is very close to zero. At most, they’d push back and have further discussion about the language choice, but once everyone gets on the same page, they’d use the specified language, no?

The author is making up a human flaw and seeing it in LLMs.

bee_rider• 3 months ago

It makes sense that these LLMs are mimicking the human-ish failure-modes because they are trained on human writing. But, at some point the company ought to be selling the behavior of the tool, not the customer. If the tool produces outputs that aren’t consistent with the constraints the user put in, how does the user get their refund?

raylad• 3 months ago

I haven’t noticed this sort of behavior with opus 4.6, but the first time I used 4.7 it decided to “simplify“ an existing piece of functionality rather than fixing it, which of course made it completely unusable.

giannicmptr1000• 3 months ago

This is very easy to instruct and modify before you start a session. The article explains that don't understand how ai responds in the style you prompt it. Probably your prompts are too human, with no instruction. Very smart people still do not understand how to us ai efficiently.

Less human AI agents, please

Related Stories