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

361–370 of 870 posts

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

#361

Post by TheRoque »

kridsdale3 wrote: post #325
Macha wrote: post #80

> - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? Starcraft and Factorio are exactly what it is not. Starcraft has a loooot of micro involved at any level beyond mid level play, despite all the "pro macros and beats gold league with mass queens" meme videos. I guess it could be like Factorio if you're playing it by plugging together blueprint books from o…

I think the StarCraft analogy is fine, you have to compare it not to macro and micro RTS play, but to INDIVIDUAL UNITS. For your whole career until now, you have been a single Zergling or Probe. Now you are the Commander.

Except that pro starcraft player still micro-manage every single Zergling or probe when necessary, while vibe coders just right click on the ennemy base and hope it'll go well

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

#362

Post by r-w »

hyperadvanced wrote: post #336
Havoc wrote: post #309

Earlier quoted context omitted.

> it lacks the meta cognition to ask 'hey, is there a better way to do this?'. Recently had an AI tell me this code (that it wrote) is a mess and suggested wiping it and starting from scratch with a more structure plan. That seems to hint at some meta cognition outlines

Metacognition As A Service, you say?

I think that’s called “consulting”.

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

#363

Post by codyb »

BeetleB wrote: post #237
cyode wrote: post #195

Earlier quoted context omitted.

This quote stuck out to me as well, for a slightly different reason. The “tenacity” referenced here has been, in my opinion, the key ingredient in the secret sauce of a successful career in tech, at least in these past 20 years. Every industry job has its intricacies, but for every engineer who earned their pay with novel work on a new protocol, framework, or paradigm, there were 10 or more providing value by putting…

This is a major concern for junior programmers. For many senior ones, after 20 (or even 10) years of tenacious work, they realize that such work will always be there, and they long ago stopped growing on that front (i.e. they had already peaked). For those folks, LLMs are a life saver. At a company I worked for, lots of senior engineers become managers because they no longer want to obsess over whether their algorith…

I feel like if you're really spending a ton of time on off by one errors after twenty years in the field you haven't actually grown much and have probably just spent a ton of time in a single space.

Otherwise you'd be senior staff to principle range and doing architecture, mentorship, coordinating cross team work, interviewing, evaluating technical decisions, etc.

I got to code this week a bit and it's been a tremendous joy! I see many peers at similar and lower levels (and higher) who have more years and less technical experience and still write lots of code and I suspect that is more what you're talking about. In that case, it's not so much that you've peaked, it's that there's not much to learn and you're doing a bunch of the same shit over and over and that's of course tiring.

I think it also means that everything you interact with outside your space does feel much harder because of the infrequency with which you have interacted with it.

If you've spent your whole career working the whole stack from interfaces to infrastructure then there's really not going to be much that hits you as unfamiliar after a point. Most frameworks recycle the same concepts and abstractions, same thing with programming languages, algorithms, data management etc.

But if you've spent most of your career in one space cranking tickets, those unknown corners are going to be as numerous as the day you started and be much more taxing.

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

#364

Post by olafalo »

nsainsbury wrote: post #168

Touching on the atrophy point, I actually wrote a few thoughts about this yesterday: https://www.neilwithdata.com/outsourced-thinking I actually disagree with Andrej here re: "Generation (writing code) and discrimination (reading code) are different capabilities in the brain." and I would argue that the only reason he can read code fluently, find issues, etc. is because he has spent year in a non-AI assisted world wr…

Thanks, this rings true to me. The struggle is an investment, and it pays off in good judgement and taste. The same goes for individual codebases too. When I see some weird bug and can immediately guess what’s going wrong and why, that’s my time spent in that codebase paying off. I guess LLM-ing a feature is the inverse, incurring some kind of cognitive debt.

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

#365

Post by overfeed »

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…

> Eventually it was easier just to quit fighting it and let it do things the way it wanted.

I wouldn't have believed it a few tears ago if you told me the industry would one day, in lockstep, decide that shipping more tech-debt is awesome. If the unstated bet doesn't pay off, that is, AI development will outpace the rate it generates cruft, then there will be hell to pay.

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

#366

Post by guy4261 »

hyperadvanced wrote: post #336
Havoc wrote: post #309

Earlier quoted context omitted.

> it lacks the meta cognition to ask 'hey, is there a better way to do this?'. Recently had an AI tell me this code (that it wrote) is a mess and suggested wiping it and starting from scratch with a more structure plan. That seems to hint at some meta cognition outlines

Metacognition As A Service, you say?

Running on the Meta Cognition Protocol server near you.

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

#367

Post by gverrilla »

bluGill wrote: post #113
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.

I've been trying Claude on my large code base today. When I give it the requirements I'd give an engineer and so "do it" it just writes garbage that doesn't make sense and doesn't seem to even meet the requirements (if it does I can't follow how - though I'll admit to giving up before I understood what it did, and I didn't try it on a real system). When I forced it to step back and do tiny steps - in TDD write one te…

it's all about the context. observe what files it opened, etc. good luck

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

#368

Post by strange_quark »

q3k wrote: post #211
uejfiweun wrote: post #31

Honestly, how long do you guys think we have left as SWEs with high pay? Like the SWE job will still exist, but with a much lower technical barrier of entry, it strikes me that the pay is going to decrease a lot. Obviously BigCo codebases are extremely complex, more than Claude Code can handle right now, but I'd say there's definitely a timer running here. The big question for my life personally is whether I can reac…

I think the pay is going to skyrocket for senior devs within a few years, as training juniors that can graduate past pure LLM usage becomes more and more difficult. Day after day the global quality of software and learning resources will degrade as LLM grey goo consumes every single nook and cranny of the Internet. We will soon see the first signs of pure cargo cult design patterns, conventions and schemes that LLMs…

Yeah, all of this. Plus companies have avoided hiring and training juniors for 3 or 4 years now (which is more related to interest rates than AI). Plus existing seniors who deskill themselves by outsourcing their brain to AI. Seniors who know actually what they're doing are going to be in greater demand.

That is assuming that LLMs plateau in capability, if they haven't already, which I think is highly likely.

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

#370

Post by codyb »

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 there's a place for both.

We have services deployed globally serving millions of customers where rigor is really important.

And we have internal users who're building browser extensions with AI that provide valuable information about the interface they're looking at including links to the internal record management, and key metadata that's affecting content placement.

These tools could be handed out on Zip drives in the street and it would just show our users some of the metadata already being served up to them, but it's amazing to strip out 75% of the process of certain things and just have our user (in this case though, it's one user who is driving all of this, so it does take some technical inclination) build out these tools that save our editors so much time when doing this before would have been months and months and months of discovery and coordination and designs that probably wouldn't actually be as useful in the end after the wants of the user are diluted through 18 layers of process.

Post reply on HN