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

431–440 of 870 posts

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

#431

Post by ActorNightly »

kshri24 wrote: post #343

Agree with Karpathy's take. Finally a down to Earth analysis from a respected source in the AI space. I guess I'll be using slopocalypse a lot more now :) > I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media It has arrived. Github will be most affected thanks to git-terrorists at Apna College refusing to take down that stupid tutor…

The respect is unwarranted.

He ran Teslas ML division, but still doesnt know what a simple kalman filter is (in the sense where he claimed that lidar would be hard to integrate with cameras).

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

#432

Post by madhadron »

CSMastermind wrote: post #413
porise wrote: post #21

I wish the people who wrote this let us know what king of codebases they are working on. They seem mostly useless in a sufficiently large codebase especially when they are messy and interactions aren't always obvious. I don't know how much better Claude is than ChatGPT, but I can't get ChatGPT to do much useful with an existing large codebase.

Are you using Codex? I'm not sure how big your repos are but I've been effective working with repos that have thousands of files and tens of thousands of lines of code. If you're just prototyping it will hit wall when things get unwieldy but that's normally a sign that you need to refactor a bit. Super strict compiler settings, static analysis, comprehensive tests, and documentation help a lot. As does basic technica…

> tens of thousands of lines of code

Perhaps this is part of it? Tens of thousands of lines of code seems like a very small repo to me.

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

#433

Post by tgrowazay »

karlgkk wrote: post #429
einrealist wrote: post #55

> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. Somewhere, there are GPUs/NPUs running hot. You send all the neces…

> And you most likely do not pay the actual costs Oh my lord you absolutely do not. The costs to oai per token inference ALONE are at least 7x. AT LEAST and from what I’ve heard, much higher.

We can observe how much generic inference providers like deepinfra or together-ai charge for large SOTA models. Since they are not subsidized and they don’t charge 7x of OpenAI, that means OAI also doesn’t have outrageously high per-token costs.

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

#434

Post by jamauro »

mkozlows wrote: post #57
atonse wrote: post #11

> LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. I’ve always said I’m a builder even though I’ve also enjoyed programming (but for an outcome, never for the sake of the code) This perfectly sums up what I’ve been observing between people like me (builders) who are ecstatic about this new world and programmers who talk about the craft of programming…

I think he's really getting at something there. I've been thinking about this a lot (in the context of trying to understand the persistent-on-HN skepticism about LLMs), and the framing I came up with[1] is top-down vs. bottom-up dev styles, aka architecting code and then filling in implementations, vs. writing code and having architecture evolve. [1] https://www.klio.org/theory-of-llm-dev-skepticism/

I like this framing. Nice typography btw, a pleasure to read.

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

#435

Post by erelong »

> 80% agent coding

A lot of these things sound cool but sometimes I'm curious what they're actually building

Like, is their bottleneck creativity now then? Are they building naything interedting or using agents to build... things that don't appeal to me, anyway?

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

#436

Post by simianwords »

maest wrote: post #346
simianwords wrote: post #117

Earlier quoted context omitted.

interesting post. i wonder if these people go back and introspect on how incorrect they have been? do they feel the need to address it?

Do _you_ do that?

i try to yes

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

#437

Post by HNisCIS »

teaearlgraycold wrote: post #380
ctoth wrote: post #112

Earlier quoted context omitted.

> But anyway, it already costs half compared to last year You could not have bought Claude Opus 4.5 at any price one year ago I'm quite certain. The things that were available cost half of what they did then, and there are new things available. These are both true. I'm agreeing with you, to be clear. There are two pieces I expect to continue: inference for existing models will continue to get cheaper. Models will con…

As a user of LLMs since GPT-3 there was noticeable stagnation in LLM utility after the release of GPT-4. But it seems the RLHF, tool calling, and UI have all come together in the last 12 months. I used to wonder what fools could be finding them so useful to claim a 10x multiplier - even as a user myself. These days I’m feeling more and more efficiency gains with Claude Code.

That's the thing people are missing, the models plateaued a while ago, still making minor gains to this day, but not huge ones. The difference is now we've had time to figure out the tooling. I think there's still a ton of ground to cover there and maybe the models will improve given that the extra time, but I think it's foolish to consider people who predicted that completely wrong. There are also a lot of mathematical concerns that will cause problems in the near and distant future. Infinite progress is far from a given, we're already way behind where all the boosters thought we'd be my now.

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

#438

Post by tayo42 »

runarberg wrote: post #422
sosomoxie wrote: post #323

Earlier quoted context omitted.

I've gone years without coding and when I come back to it, it's like riding a bike! In each iteration of my coding career, I have become a better developer, even after a large gap. Now I can "code" during my gap. Were I ever to hand-code again, I'm sure my skills would be there. They don't atrophy, like your ability to ride a bike doesn't atrophy. Yes you may need to warm back up, but all the connections in your brai…

Have you ever learnt a foreign language (say Mongolian, or Danish) and then never spoken it, nor even read anything in it for over 10 years? It is not like riding a bike, it doesn’t just come back like that. You have to actually relearn the language, practice it, and you will suck at it for months. Comprehension comes first (within weeks) but you will be speaking with grammatical errors, mispronunciations, etc. for m…

Anecdotally, i burned out pretty hard and basically didn't open a text editor for half a year (unemployed too). Eventually i got an itch to write code again and it didn't really feel like I was really worse. Maybe it wasn't long enough atrophy but code doesn't seem to quite work like language though ime.

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

#439

Post by FeepingCreature »

monkaiju wrote: post #347
atonse wrote: post #11

> LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. I’ve always said I’m a builder even though I’ve also enjoyed programming (but for an outcome, never for the sake of the code) This perfectly sums up what I’ve been observing between people like me (builders) who are ecstatic about this new world and programmers who talk about the craft of programming…

So far I haven't seen it actually be effective at "building" in a work context with any complexity, and this despite some on our team desperately trying to make that the case.

I have! You have to be realistic about the projects. The more irreducible local context it needs, the less useful it will be. Great for greenfield code, oneshots, write once read once run for months.

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

#440

Post by solumunus »

gritspants wrote: post #172
daxfohl wrote: post #65

I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…

My disillusionment comes from the feeling I am just cosplaying my job. There is nothing to distinguish one cosplayer from another. I am just doordashing software, at this point, and I'm not in control.

I don’t get this at all. I’m using LLM’s all day and I’m constantly having to make smart architectural choices that other less experienced devs won’t be making. Are you just prompting and going with whatever the initial output is, letting the LLM make decisions? Every moderately sized task should start with a plan, I can spend hours planning, going off and thinking, coming back to the plan and adding/changing things, etc. Sometimes it will be days before I tell the LLM to “go”. I’m also constantly optimising the context available to the LLM, and making more specific skills to improve results. It’s very clear to me that knowledge and effort is still crucial to good long term output… Not everyone will get the same results, in fact everyone is NOT getting the same results, you can see this by reading the wildly different feedback on HN. To some LLM’s are a force multiplier while others claim they can’t get a single piece of decent output…

I think the way you’re using these tools that makes you feel this way is a choice. You’re choosing to not be in control and do as little as possible.

Post reply on HN