[Tade0]

> The benefits we get from checking in with other humans, like error correction, and delegation can all be done better by AI.

Not this generation of AI though. It's a text predictor, not a logic engine - it can't find actual flaws in your code, it's just really good at saying things which sound plausible.

[xnorswap]

> it can't find actual flaws in your code

I can tell from this statement that you don't have experience with claude-code.

It might just be a "text predictor" but in the real world it can take a messy log file, and from that navigate and fix issues in source.

It can appear to reason about root causes and issues with sequencing and logic.

That might not be what is actually happening at a technical level, but it is indistinguishable from actual reasoning, and produces real world fixes.

[Tade0]

> I can tell from this statement that you don't have experience with claude-code.

I happen to use it on a daily basis. 4.6-opus-high to be specific.

The other day it surmised from (I assume) the contents of my clipboard that I want to do A, while I really wanted to B, it's just that A was a more typical use case. Or actually: hardly anyone ever does B, as it's a weird thing to do, but I needed to do it anyway.

> but it is indistinguishable from actual reasoning

I can distinguish it pretty well when it makes mistakes someone who actually read the code and understood it wouldn't make.

Mind you: it's great at presenting someone else's knowledge and it was trained on a vast library of it, but it clearly doesn't think itself.

[weird-eye-issue]

What do you mean the content of your clipboard?

[Tade0]

I either accidentally pasted it somewhere and removed, forgetting about doing that or it's reading the clipboard.

The suggestion it gave me started with the contents of the clipboard and expanded to scenario A.

[elar_verole]

Sorry to sound rude - but you polluted the context, pointing to the fact you would like A, and then found it annoying it tried to do A ?

[emp17344]

Oh, please. There’s always a way to blame the user, it’s a catch-22. The fact is that coding agents aren’t perfect and it’s quite common for them to fail. Refer to the recent C-compiler nonsense Anthropic tried to pull for proof.

[project2501a]

I know I am not supposed to be negative in HN, but lay off the koolaid, dear colleague.

[weird-eye-issue]

So you don't even know what your prompt was and you think it might be secretly reading your clipboard and you expect people to take you seriously?

[LoganDark]

What you're describing is not finding flaws in code. It's summarizing, which current models are known to be relatively good at.

It is true that models can happen to produce a sound reasoning process. This is probabilistic however (moreso than humans, anyway).

There is no known sampling method that can guarantee a deterministic result without significantly quashing the output space (excluding most correct solutions).

I believe we'll see a different landscape of benefits and drawbacks as diffusion language models begin to emerge, and as even more architectures are invented and practiced.

I have a tentative belief that diffusion language models may be easier to make deterministic without quashing nearly as much expressivity.

[michaelscott]

Nothing you've said about reasoning here is exclusive to LLMs. Human reasoning is also never guaranteed to be deterministic, excluding most correct solutions. As OP says, they may not be reasoning under the hood but if the effect is the same as a tool, does it matter?

I'm not sure if I'm up to date on the latest diffusion work, but I'm genuinely curious how you see them potentially making LLMs more deterministic? These models usually work by sampling too, and it seems like the transformer architecture is better suited to longer context problems than diffusion

[LoganDark]

The way I imagine greedy sampling for autoregressive language models is guaranteeing a deterministic result at each position individually. The way I'd imagine it for diffusion language models is guaranteeing a deterministic result for the entire response as a whole. I see diffusion models potentially being more promising because the unit of determinism would be larger, preserving expressivity within that unit. Additionally, diffusion language models iterate multiple times over their full response, whereas autoregressive language models get one shot at each token, and before there's even any picture of the full response. We'll have to see what impact this has in practice; I'm only cautiously optimistic.

[michaelscott]

I guess it depends on the definition of deterministic, but I think you're right and there's strong reason to expect this will happen as they develop. I think the next 5 - 10 years will be interesting!

[MrOrelliOReilly]

This all sounds like the stochastic parrot fallacy. Total determinism is not the goal, and it not a prerequisite for general intelligence. As you allude to above, humans are also not fully deterministic. I don't see what hard theoretical barriers you've presented toward AGI or future ASI.

[LoganDark]

I haven't heard the stochastic parrot fallacy (though I have heard the phrase before). I also don't believe there are hard theoretical barriers. All I believe is that what we have right now is not enough yet. (I also believe autoregressive models may not be capable of AGI.)

[emp17344]

Did you just invent a nonsense fallacy to use as a bludgeon here? “Stochastic parrot fallacy” does not exist, and there actually quite a bit of evidence supporting the stochastic parrot hypothesis.

[LoganDark]

I imagine "stochastic parrot fallacy" could be their term for using the hypothesis to dismiss LLMs even where they can be useful; i.e., dismissing them for their weaknesses alone and ignoring their strengths. (Of course, we have no way to know for sure without their input.)

[MrOrelliOReilly]

Correct, I am stating that the stochastic parrot hypothesis is a fallacy.

[nielsole]

> moreso than humans

Citation needed.

[LoganDark]

Much of the space of artificial intelligence is based on a goal of a general reasoning machine comparable to the reasoning of a human. There are many subfields that are less concerned with this, but in practice, artificial intelligence is perceived to have that goal.

I am sure the output of current frontier models is convincing enough to outperform the appearance of humans to some. There is still an ongoing outcry from when GPT-4o was discontinued from users who had built a romantic relationship with their access to it. However I am not convinced that language models have actually reached the reliability of human reasoning.

Even a dumb person can be consistent in their beliefs, and apply them consistently. Language models strictly cannot. You can prompt them to maintain consistency according to some instructions, but you never quite have any guarantee. You have far less of a guarantee than you could have instead with a human with those beliefs, or even a human with those instructions.

I don't have citations for the objective reliability of human reasoning. There are statistics about unreliability of human reasoning, and also statistics about unreliability of language models that far exceed them. But those are both subjective in many cases, and success or failure rates are actually no indication of reliability whatsoever anyway.

On top of that, every human is different, so it's difficult to make general statements. I only know from my work circles and friend circles that most of the people I keep around outperform language models in consistency and reliability. Of course that doesn't mean every human or even most humans meet that bar, but it does mean human-level reasoning includes them, which raises the bar that models would have to meet. (I can't quantify this, though.)

There is a saying about fully autonomous self driving vehicles that goes a little something like: they don't just have to outperform the worst drivers; they have to outperform the best drivers, for it to be worth it. Many fully autonomous crashes are because the autonomous system screwed up in a way that a human would not. An autonomous system typically lacks the creativity and ingenuity of a human driver.

Though they can already be more reliable in some situations, we're still far from a world where autonomous driving can take liability for collisions, and that's because they're not nearly as reliable or intelligent enough to entirely displace the need for human attention and intervention. I believe Waymo is the closest we've gotten and even they have remote safety operators.

[throwway120385]

It's not enough for them to be "better" than a human. When they fail they also have to fail in a way that is legible to a human. I've seen ML systems fail in scenarios that are obvious to a human and succeed in scenarios where a human would have found it impossible. The opposite needs to be the case for them to be generally accepted as equivalent, and especially the failure modes need to be confined to cases where a human would have also failed. In the situations I've seen, customers have been upset about the performance of the ML model because the solution to the problem was patently obvious to them. They've been probably more upset about that than about situations where the ML model fails and the end customer also fails.

[gaigalas]

That's not a citation.

[LoganDark]

It's roughly why I think this way, along with a statement that I don't have objective citations. So sure, it's not a citation. I even said as much, right in the middle there.

[emp17344]

That’s because there’s no objective research on this. Similarly, there are no good citations to support your objection. They simply don’t exist yet.

[weego]

And not this or any existing generation of people. We're bad a determining want vs need, being specific, genericizing our goals into a conceptual framework of existing patterns and documenting & explaining things in a way that gets to a solid goal.

The idea that the entire top down processes of a business can be typed into an AI model and out comes a result is again, a specific type of tech person ideology that sees the idea of humanity as an unfortunate annoyance in the process of delivering a business. The rest of the world see's it the other way round.

[afro88]

I would have agreed with you a year ago

[lpapez]

If you only realized how ridiculous your statement is, you never would have stated it.

[jychang]

It's also literally factually incorrect. Pretty much the entire field of mechanistic interpretability would obviously point out that models have an internal definition of what a bug is.

Here's the most approachable paper that shows a real model (Claude 3 Sonnet) clearly having an internal representation of bugs in code: https://transformer-circuits.pub/2024/scaling-monosemanticit...

Read the entire section around this quote:

> Thus, we concluded that 1M/1013764 represents a broad variety of errors in code.

(Also the section after "We find three different safety-relevant code features: an unsafe code feature 1M/570621 which activates on security vulnerabilities, a code error feature 1M/1013764 which activates on bugs and exceptions")

This feature fires on actual bugs; it's not just a model pattern matching saying "what a bug hunter may say next".

[mrbungie]

Was this "paper" eventually peer reviewed?

PS: I know it is interesting and I don't doubt Antrophic, but for me it is so fascinating they get such a pass in science.

[jychang]

This is more of an article describing their methodology than a full paper. But yes, there's plenty of peer reviewed papers on this topic, scaling sparse autoencoders to produce interpretable features for large models.

There's a ton of peer reviewed papers on SAEs in the past 2 years; some of them are presented at conferences.

For example: "Sparse Autoencoders Find Highly Interpretable Features in Language Models" https://proceedings.iclr.cc/paper_files/paper/2024/file/1fa1...

"Scaling and evaluating sparse autoencoders" https://iclr.cc/virtual/2025/poster/28040

"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning" https://proceedings.neurips.cc/paper_files/paper/2024/hash/c...

"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2" https://aclanthology.org/2024.blackboxnlp-1.19.pdf

[ACCount37]

Modern ML is old school mad science.

The lifeblood of the field is proof-of-concept pre-prints built on top of other proof-of-concept pre-prints.

[emp17344]

Sounds like you agree this “evidence” lacks any semblance of scientific rigor?

[mrbungie]

(Not GP) There was a well recognized reproducibility problem in the ML field before LLM-mania, and that's considering published papers with proper peer-reviews. The current state of afairs in some ways is even less rigourous than that, and then some people in the field feel free to overextend their conclusions into other fields like neurosciences.

[ACCount37]

Frankly, I don't see a reason to give a shit.

We're in the "mad science" regime because the current speed of progress means adding rigor would sacrifice velocity. Preprints are the lifeblood of the field because preprints can be put out there earlier and start contributing earlier.

Anthropic, much as you hate them, has some of the best mechanistic interpretability researchers and AI wranglers across the entire industry. When they find things, they find things. Your "not scientifically rigorous" is just a flimsy excuse to dismiss the findings that make you deeply uncomfortable.

[Jensson]

> This feature fires on actual bugs; it's not just a model pattern matching saying "what a bug hunter may say next".

You don't think a pattern matcher would fire on actual bugs?

[emp17344]

Mechanistic interpretability is a joke, supported entirely by non-peer reviewed papers released as marketing material by AI firms.

[pousada]

Some people are still stuck in the “stochastic parrot” phase and see everything regarding LLMs through that lense.

[windexh8er]

Current LLMs do not think. Just because all models anthropomorphize the repetitive actions a model is looping through does not mean they are truly thinking or reasoning.

On the flip side the idea of this being true has been a very successful indirect marketing campaign.

[pousada]

What does “truly thinking or reasoning” even mean for you?

I don’t think we even have a coherent definition of human intelligence, let alone of non-human ones.

[chpatrick]

Everyone knows to really think you need to use your fleshy meat brain, everything else is cheating.

[windexh8er]

Oh, yes. The trope of "but what does it even mean to think".

If you can't speak, can you think? Yes. Large Language model. Thinking is not predicated on language.

A few good starts for you. Please refute all of these arguments in your spare time to convince me otherwise:

* https://machinelearning.apple.com/research/illusion-of-think... * https://archive.is/FM4y8 * https://www.raspberrypi.org/blog/secondary-school-maths-show...

[pousada]

My point was not that I’m 100% convinced that LLMs can think or are intelligent.

My point was that we don’t have a great definition for (human) intelligence either. The articles you posted also don’t seem to be too confident in what human intelligence actually entails.

See https://en.wikipedia.org/wiki/Intelligence

> There is controversy over how to define intelligence. Scholars describe its constituent abilities in various ways, and differ in the degree to which they conceive of intelligence as quantifiable.

Given that an LLM isn’t even human but essentially an alien entity, who can confidently say they are intelligent or not?

I’m very sceptic of those who are very convinced one or the other way.

Are LLMs intelligent in the way that humans are? I’m quite sure they aren’t.

Are LLMs just stochastic parrots? I don’t find that framing convincing anymore either.

Either way it’s not clear, just check how this topic is discussed daily in most frontpage threads for the last couple of years

[p-e-w]

You’re committing the classic fallacy of confusing mechanics with capabilities. Brains are just electrons and chemicals moving through neural circuits. You can’t infer constraints on high-level abilities from that.

[Tade0]

This goes both ways. You can't assume capabilities based on impressions. Especially with LLMs, which are purpose built to give an impression of producing language.

Also, designers of these systems appear to agree: when it was shown that LLMs can't actually do calculations, tool calls were introduced.

[AlecSchueler]

It's true that they only give plausible sounding answers. But let's say we ask a simple question like "What's the sum of two and two?" The only plausible sounding answer to that will be "four." It doesn't need to have any fancy internal understanding or anything else beyond prediction to give what really is the same answer.

The same goes for a lot of bugs in code. The best prediction is often the correct answer, being the highlighting of the error. Whether it can "actually find" the bugs—whatever that means—isn't really so important as whether or not it's correct.

[Tade0]

It becomes important the moment your particular bug is on one hand typical, but has a non-typical reason. In such cases you'll get nonsense which you need to ignore.

Again - they're very useful, as they give great answers based on someone else's knowledge and vague questions on part of the user, but one has to remain vigilant and keep in mind this is just text presented to you to look as believable as possible. There's no real promise of correctness or, more importantly, critical thinking.

[AlecSchueler]

100% They're not infallible but that's a different argument to "they can't find bugs in your code."

[nazgul17]

While I agree, if you think that AI is just a text predictor, you are missing an important point.

Intelligence, can be borne of simple targets, like next token predictor. Predicting the next token with the accuracy it takes to answer some of the questions these models can answer, requires complex "mental" models.

Dismissing it just because its algorithm is next token prediction instead of "strengthen whatever circuit lights up", is missing the forest for the trees.

[laichzeit0]

Absolutely nuts, I feel like I'm living in a parallel universe. I could list several anecdotes here where Claude has solved issues for me in an autonomous way that (for someone with 17 years of software development, from embedded devices to enterprise software) would have taken me hours if not days.

To the nay sayers... good luck. No group of people's opinions matter at all. The market will decide.

[xnorswap]

I wonder if the parent comments remark is a communication failure or pedantry gone wrong, because like you, claude-code is out there solving real problems and finding and fixing defects.

A large quantity of bugs as raised are now fixed by claude automatically from just the reports as written. Everything is human reviewed and sometimes it fixes it in ways I don't approve, and it can be guided.

It has an astonishing capability to find and fix defects. So when I read "It can't find flaws", it just doesn't fit my experience.

I have to wonder if the disconnect is simply in the definition of what it means to find a flaw.

But I don't like to argue over semantics. I don't actually care if it is finding flaws by the sheer weight of language probability rather than logical reasoning, it's still finding flaws and fixing them better than anything I've seen before.

[gilbetron]

I can't control random internet people, but within my personal and professional life, I see the effective pattern of comparing prompts/contexts/harnesses to figure out why some are more effective than others (in fact tooling is being developed in the AI industry as a whole to do so, claude even added the "insights" command).

I feel that many people that don't find AI useful are doing things like, "Are there any bugs in this software?" rather than developing the appropriate harness to enable the AI to function effectively.

[cyberpunk]

I think it’s just fear, I sure know that after 25 years as a developer with a great salary and throughout all that time never even considering the chance of ever being unemployable I’m feeling it too.

I think some of us come to terms with it in different ways.

[hparadiz]

I used to sometimes get stuck on a problem for weeks and then get a budget pulled or get put on another project. Sometimes those issues never did get solved. Or have to tell someone sorry I don't have capacity to solve a problem for you. Now a lot of that anxiety has been replaced with a more can do attitude. Like wouldn't being able to pull off results create more opportunity?

[ACCount37]

Your brain is a slab of wet meat, not a logic engine. It can't find actual flaws in your code - it's just half-decent at pattern recognition.

[gaigalas]

That is not exactly true. The brain does a lot of things that are not "pattern recognition".

Simpler, more mundane (not exactly, still incredibly complicated) stuff like homeostasis or motor control, for example.

Additionally, our ability to plan ahead and simulate future scenarios often relies on mechanisms such as memory consolidation, which are not part of the whole pattern recognition thing.

The brain is a complex, layered, multi-purpose structure that does a lot of things.

[mexicocitinluez]

Its pattern recognition all the way down.