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

A few random notes from Claude coding quite a bit last few weeks

twitter.com

Post reply on HN
Print view View original

831–840 of 870 posts

Re: A few random notes from Claude coding quite a bit last few weeks

#831

Post by ben_w »

TeMPOraL wrote: post #830
ben_w wrote: post #829

Earlier quoted context omitted.

Only if we're lucky and the LLMs cease being replaced with improved models. Claude has already shown us people who openly say "I don't code and yet I managed this"; right now the command line UI will scare off a lot of people, and people using the LLMs still benefit from technical knowledge and product design skills, if the tools don't improve we keep that advantage… …but how long will it be before the annoyingly ign…

> using the LLMs still benefit from technical knowledge and product design skills, if the tools don't improve we keep that advantage… I don't think we will, because many of us are already asking LLMs for help/advice on these, so we're already close to the point where LLMs will be able to use these capabilities directly, instead of just for helping us drive the process.

Indeed, but the output of LLMs today for these kinds of task are akin to a junior product designer, a junior project manager, a junior software architect etc.

For those of us who are merely amateur at any given task, LLMs raising us to "junior" is absolutely an improvement. But just as it's possible to be a better coder than an LLM, if you're a good PM or QA or UI/UX designer, you're not obsolete yet.

Re: A few random notes from Claude coding quite a bit last few weeks

#832

Post by zelphirkalt »

fragmede wrote: post #146
gtowey wrote: post #105

Earlier quoted context omitted.

The value extortion plan writes itself. How long before someone pitches the idea that the models explicitly almost keep solving your problem to get you to keep spending? Would you even know?

The free market proposition is that competition (especially with Chinese labs and grok) means that Anthropic is welcome to do that. They're even welcome to illegally collude with OpenAi such that ChatGPT is similarly gimped. But switching costs are pretty low. If it turns out I can one shot an issue with Qwen or Deepseek or Kimi thinking, Anthropic loses not just my monthly subscription, but everyone else's I show th…

And we all know the market always gives us the best quality product ...

Re: A few random notes from Claude coding quite a bit last few weeks

#833

Post by testaccount28 »

meowface wrote: post #428
testaccount28 wrote: post #129

Earlier quoted context omitted.

you are using it on easy questions. some of us are not.

A lot of people are getting good results using it on hard things. Obviously not perfect, but > 50% success. That said, more and more people seem to be arriving at the conclusion that if you want a fairly large-sized, complex task in a large existing codebase done right, you'll have better odds with Codex GPT-5.2-Codex-XHigh than with Claude Code Opus 4.5. It's far slower than Opus 4.5 but more likely to get things co…

yes, i also get good results. that's why i use it on the hard things.

Re: A few random notes from Claude coding quite a bit last few weeks

#834

Post by Jean-Papoulos »

>Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

If this is how all juniors are learning nowadays, seniors are going shot up in value in the next decade.

Re: A few random notes from Claude coding quite a bit last few weeks

#835

Post by taylorius »

pvab3 wrote: post #705
taylorius wrote: post #696

Earlier quoted context omitted.

Why can LLMs not be responsible for things? (genuine question - I'm not certain myself).

because it doesn't have any skin in the game and can't be punished, and can't be rewarded for succeeding. Its reputation, career, and dignity are nonexistent.

On the contrary - the LLM has had it's own version of "skin in the game" through the whole of it's training. Reinforcement learning is nothing but that. Why is that less real than putting a person in prison. Is it because of the LLM itself, or because you don't trust the people selling it to you?

Re: A few random notes from Claude coding quite a bit last few weeks

#836

Post by duncangh »

Applejinx wrote: post #795
rurp wrote: post #395

Earlier quoted context omitted.

Perhaps. I've had LLMs tell me some code is deeply flawed garbage that should be rewritten about code that exact same LLM wrote minutes before. It could be a sign of deep meta cognition, or it might be due to some cognitive gaps where it has no idea why it did something a minute ago and suddenly has a different idea.

This is not a fair criticism. There is _nobody_ there, so you can't be saying 'code the exact same LLM wrote minutes before'. There is no 'exact same LLM' and no ideas for it to have, you're trying to make sense of sparkles off the surface of a pond. There's no 'it' to have an idea and then a different idea, much less deep meta cognition.

They should’ve named him tom instead of Claude in homage to Ten second Tom from fifty first dates

Re: A few random notes from Claude coding quite a bit last few weeks

#837

Post by cagenut »

daxfohl wrote: post #807
cagenut wrote: post #783

Earlier quoted context omitted.

after a decade of follow-the-sun deployments by php contractors from vietnam to costa rica where our only qa was keeping an eye on the 500s graph, ai can't scare me.

That's actually a good comparison. Though even then, I imagine you at least have the ability to get on the phone and ask what they just did. Whereas LLM would just be like, "IDK, that was my twin brother. I'd ask him directly, but unfortunately he has been garbage collected. It was very sad. Would you like a cookie?" I wonder if there's any value in some system that preserves the chat context of a coding agent and ta…

it was basically a mindless loop, very prime for being agent driven:

  - observe error rate uptick
  - maybe dig in with apm tooling
  - read actual error messages
  - compare what apm and logs said to last commit/deploy
  - if they look even tangentially related deploy the previous commit (aka revert)
  - if its still not fixed do a "debug push", basically stuff a bunch of print statements (or you can do better) around the problem to get more info
I won't say that solves every case but definitely 90% of them.

I think your point about preserving some amount of intent/context is good, but also like what are most of us doing with agents if not "loop on error message until it goes away".

Re: A few random notes from Claude coding quite a bit last few weeks

#838

Post by infecto »

Draiken wrote: post #789
infecto wrote: post #604

Earlier quoted context omitted.

I think you have to be aware of how you use any tool but I don’t think this is a forever treadmill. It’s pretty clear to me since early on that the goal is for you the user to not have to craft the perfect prompt. At least for my workflow it’s pretty darn close to that for me.

If it ever gets there, then anyone can use it and there's no "skill" to be learned at all. Either it will continue to be this very flawed non-deterministic tool that requires a lot of effort to get useful code out of it, or it will be so good it'll just work. That's why I'm not gonna heavily invest my time into it.

Good for you. Others like myself find the tools incredibly useful. I am able to knock out code at a higher cadence and it’s meeting a standard of quality our team finds acceptable.

Re: A few random notes from Claude coding quite a bit last few weeks

#839

Post by TeMPOraL »

Antibabelic wrote: post #537
TeMPOraL wrote: post #484

Earlier quoted context omitted.

> Vendors of small utilities could be in trouble. For example I needed to cut out some pages from a pdf. I could have found a tool online(I’m sure there are several), write one myself. However, Claude quickly performed the task. Definitely. Making small, single-purpose utilities with LLMs is almost as easy these days as googling for them on-line - much easier, in fact, if you account for time spent filtering out all…

Whatever happened to just typing "apt install qrencode"? It's definitely "fast, reliable, free of surveillance economy bullshit, and doesn't employ URL shorteners".

1) This was for my wife. She is not proficient in Linux or CLI in general, and (like ~all white collar workers these days) works almost exclusively in browser tools (exception being pre-O365 versions of Word and Excel we keep running on her laptop because she prefers them).

2) I never heard of `qrencode` CLI tool until today. For some reason I didn't even consider it might exist (maybe because last time I checked, which was many years ago, there was none).

3) Notably, no one mentioned it the last time I shared this story on HN - https://news.ycombinator.com/item?id=44385049.

4) Even if I knew about it, I'd still have to build a web frontend for it, and I'd need a proper server for it, which I'd then have to maintain properly, and secure it against the `qrencode` call becoming an attack vector.

So frankly, for my specific problem, my solution is strictly better.

Re: A few random notes from Claude coding quite a bit last few weeks

#840

Post by TeMPOraL »

agos wrote: post #626
Antibabelic wrote: post #609

Earlier quoted context omitted.

Sure, but that's entirely different from vibe-coding a tool, which sounds like a colossal waste of resources.

as long as that wast and the associated cost is heavily subsidized as it is today, nobody will care

Don't get the anti-AI propaganda get to you too much. Inference is cheap on the margin.

Consider: there are models capable (if barely) of doing this job, that you can run locally, on a upper-mid-range PC with high-end consumer GPU. Take that as a baseline, assume it takes a day instead of an hour because of inference speed, tally up total electricity cost. It's not much. Won't boil oceans any more than people playing AAA video games all day will.

Sure, the big LLMs from SOTA vendors use more GPUs/TPUs for inference, but this means they finish much faster. Plus, commercial vendors have lots of optimizations (batch processing, large caches, etc.), and data centers are much more power-efficient than your local machine, so "how much it'd cost me in power bill if I did it locally" is a good starting estimate.

Post reply on HN