Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude is good at assembling blocks, but still falls apart at creating them

approachwithalacrity.com

Post reply on HN
Print view View original

191–200 of 249 posts

Re: Claude is good at assembling blocks, but still falls apart at creating them

#191

Post by kaffekaka »

fragmede wrote: post #146
zeroonetwothree wrote: post #132

Earlier quoted context omitted.

Why is it every time anyone has a critique someone has to say “oh but you aren’t using model X, which clearly never has this problem and is far better”? Yet the data doesn’t show all that much difference between SOTA models. So I have a hard time believing it.

Because they are getting better. They're still far from perfect/AGI/ASI, but when was the last time you saw the word "delve"? So the models are clearly changing, the question is why doesn't the data show That they're actually better? Thing is, everyone knows the benchmarks are being gamed. Exactly how is besides the point. In practice, anecdotally, Opus 4.5 is noticably better than 4, and GPT 5.2 has also noticably i…

"They dont say X as often anymore" is just a distraction, it has nothing to do with actual capability of the model.

Unfortunately, I think that the overlap between actual model improvements and what people perceive as "better" is quite small. Combine this with the fact that most people desperately want to have a strong opinion on stuff even though the factual basis is very weak.. "But I can SEE it is X now".

Re: Claude is good at assembling blocks, but still falls apart at creating them

#192

Post by patagurbon »

computerex wrote: post #184
utopiah wrote: post #177

Earlier quoted context omitted.

> The tech is moving so fast. Well that's exactly the problem : how can one say that? The entire process of evaluating what "it" actually does has been a problem from the start. Input text, output text ... OK but what if the training data includes the evaluation? This was ridiculous few years ago but then the scale went from some curated text datasets to... most of the Web as text, to most of the Web as text includin…

You know LLM's have been used to solve very hard previously unsolved math problems like some of the Erdos problems?

That Erdos problem solution is believed by quite a few to be a previous result found in the literature, just used in a slightly different way. It also seems not a lack of progress but simply no one cared to give it a go.

That’s a really fantastic capability, but not super surprising.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#193

Post by raducu »

orbital-decay wrote: post #109
Uehreka wrote: post #102

Earlier quoted context omitted.

It feels like a lot of people keep falling into the trap of thinking we’ve hit a plateau, and that they can shift from “aggressively explore and learn the thing” mode to “teach people solid facts” mode. A week ago Scott Hanselman went on the Stack Overflow podcast to talk about AI-assisted coding. I generally respect that guy a lot, so I tuned in and… well it was kind of jarring. The dude kept saying things in this r…

> in general I find GPT 5.x to actually be a huge breakthrough in terms of asserting itself when I’m wrong That's just a different bias purposefully baked into GPT-5's engineered personality on post-training. It always tries to contradict the user, including the cases where it's confidently wrong, and keeps justifying the wrong result in a funny manner if pressed or argued with (as in, it would have never made that o…

> That's just a different bias purposefully baked into GPT-5's engineered personality on post-training.

I want to highlight this realization! Just because a model says something cool, it doesn't mean it's an emergent behavior/realization, but more likely post-training.

My recent experience with claude code cli was exactly this.

It was so hyped here and elsewhere I gave it a try and I'd say it's almost arrogant/petulant.

When I pointed out bugs in long sessions it tried to gaslight me that everything was alright, faked tests to prove his point.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#194

Post by raducu »

alternatetwo wrote: post #110
Uehreka wrote: post #102

Earlier quoted context omitted.

It feels like a lot of people keep falling into the trap of thinking we’ve hit a plateau, and that they can shift from “aggressively explore and learn the thing” mode to “teach people solid facts” mode. A week ago Scott Hanselman went on the Stack Overflow podcast to talk about AI-assisted coding. I generally respect that guy a lot, so I tuned in and… well it was kind of jarring. The dude kept saying things in this r…

Claude is still just like that once you’re deep enough in the valley of the conversation. not exactly that phrase but things like that’s the smoking gun or so. nothing has changed.

> Claude is still just like that once you’re deep enough in the valley of the conversation

My experience is claude (but probably other models as well) indeed resort to all sorts of hacks once the conversation has gone for too long.

Not sure if it's an emergent behavior or something done in later stages of training to prevent it from wasting too many tokens when things are clearly not going well.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#195

Post by raducu »

overgard wrote: post #144
Uehreka wrote: post #102

Earlier quoted context omitted.

It feels like a lot of people keep falling into the trap of thinking we’ve hit a plateau, and that they can shift from “aggressively explore and learn the thing” mode to “teach people solid facts” mode. A week ago Scott Hanselman went on the Stack Overflow podcast to talk about AI-assisted coding. I generally respect that guy a lot, so I tuned in and… well it was kind of jarring. The dude kept saying things in this r…

I don't see a reason to think we're not going to hit a plateua sooner or later (and probably sooner). You can't scale your way out of hallucinations, and you can't keep raising tens of billions to train these things without investors wanting a return. Once you use up the entire internets worth of stack overflow responses and public github repositories you run into the fact that these things aren't good at doing thing…

> Once you use up the entire internets worth of stack overflow responses and public github repositories you run into the fact that these things aren't good at doing things outside their training dataset.

I think the models have reached that human training data limitation a few generations ago, yet they stil clearly improve by various other techniques.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#196

Post by ehnto »

threethirtytwo wrote: post #72
mattmanser wrote: post #61

Earlier quoted context omitted.

How do you come to that conclusion? There are absolutely tons of code pens of that style. And jsfiddles, zen gardens, etc. I think the true mind boggle is you don't seem to realize just how much content the AI conpanies have stolen.

>I think the true mind boggle is you don't seem to realize just how much content the AI conpanies have stolen. What makes you think I don't realize it? Looks like your comment was generated by an LLM because that was an hallucination that is Not true at all. AI companies have stolen a lot of content for training. I AGREE with this. So have you. That content lives rent free in your head as your memory. It's the same c…

I think you are pointing out the exact conflation here. The commentor probably didn't steal a bunch of code, because it is possible to reason from first principles and rules and still end up being able to code as a human.

It did not take me reading the entirety of available public code to be kind of okay at programming, I created my way to being kind of okay at programming. I was given some rules and worked with those, I did not mnemonic my way into logic.

None of us scraped and consumed the entire internet, is hopefully pretty obvious, but we still have capabilities in excess of AI.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#197

Post by MarginalGainz »

This mirrors my experience trying to integrate LLMs into production pipelines.

The issue seems to be that LLMs treat code as a literary exercise rather than a graph problem. Claude is fantastic at the syntax and local logic ('assembling blocks'), but it lacks the persistent global state required to understand how a change in module A implicitly breaks a constraint in module Z.

Until we stop treating coding agents as 'text predictors' and start grounding them in an actual AST (Abstract Syntax Tree) or dependency graph, they will remain helpful juniors rather than architects.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#198

Post by ehnto »

Kuinox wrote: post #36
simonw wrote: post #30

I'm not entirely convinced by the anecdote here where Claude wrote "bad" React code: > But in context, this was obviously insane. I knew that key and id came from the same upstream source. So the correct solution was to have the upstream source also pass id to the code that had key, to let it do a fast lookup. I've seen Claude make mistakes like that too, but then the moment you say "you can modify the calling code a…

> My guess is that Claude is trained to bias towards making minimal edits to solve problems. I don't have the same feeling. I find that claude tends to produce wayyyyy too much code to solve a problem, compared to other LLMs.

That has been my impression too, it takes particular guidance to get it to write concise code without too much architecture airmanship.

Re: Claude is good at assembling blocks, but still falls apart at creating them

#199

Post by fatherwavelet »

fragmede wrote: post #146
zeroonetwothree wrote: post #132

Earlier quoted context omitted.

Why is it every time anyone has a critique someone has to say “oh but you aren’t using model X, which clearly never has this problem and is far better”? Yet the data doesn’t show all that much difference between SOTA models. So I have a hard time believing it.

Because they are getting better. They're still far from perfect/AGI/ASI, but when was the last time you saw the word "delve"? So the models are clearly changing, the question is why doesn't the data show That they're actually better? Thing is, everyone knows the benchmarks are being gamed. Exactly how is besides the point. In practice, anecdotally, Opus 4.5 is noticably better than 4, and GPT 5.2 has also noticably i…

The type of person who outsources their thinking to their social media feed news stories and isn't intellectually curious enough to deeply explore the models themselves in order for the models to display their increase in strength, isn't going to be able to tell this themselves.

I would think this also correlates with the type of person who hasn't done enough data analysis themselves to understand all the lies and misleading half-truths "data" often tells. In the reverse also, that experience with data inoculates one to some degree against the bullshitting LLM so it is probably easier to get value from the model.

I would imagine there are all kinds of factors like this that multiple so some people are really having vastly different experiences with the models than others.

Post reply on HN