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

541–550 of 870 posts

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

#541

Post by carimura »

raducu wrote: post #453
striking wrote: post #118

Earlier quoted context omitted.

It's not just brain atrophy, I think. I think part of it is that we're actively making a tradeoff to focus on learning how to use the model rather than learning how to use our own brains and work with each other. This would be fine if not for one thing: the meta-skill of learning to use the LLM depreciates too. Today's LLM is gonna go away someday, the way you have to use it will change. You will be on a forever trea…

> let myself atrophy, run on a treadmill forever, for something You're lucky to afford the luxury not to atrophy. It's been almost 4 years since my last software job interview and I know the drills about preparing for one. Long before LLMs my skills naturally atrophy in my day job. I remember the good old days of J2ME of writing everything from scratch. Or writing some graph editor for universiry, or some speculative…

Ya I agree it's totally crazy.... but, do most app deployments need even half that stuff? I feel like most apps at most companies can just build an app and deploy it using some modern paas-like thing.

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

#542

Post by mlrtime »

taytus wrote: post #502
viccis wrote: post #213

Earlier quoted context omitted.

Same. This kind of coding feels like it got rid of the building aspect of programming that always felt nice, and it replaced it entirely with business logic concerns, product requirements, code reviews, etc. All the stuff I can generally take or leave. It's like I'm always in a meeting. >If I was intellectually excited about telling something to do this for me, I'd have gotten into management. Exactly this. This is t…

Because you are not coding, you are building. I've been coding since I was 7 years old, now I'm building.

I'd go one step higher, we're not builders, we're problem solvers.

Sometimes the problem needs building, sometimes not.

I'm an Engineer, I see a problem and want to solve it. I don't care if I have to write code, have a llm build something new, or maybe even destroy something. I want to solve the problem for the business and move to the next one, most of the time it is having a llm write code though.

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

#543

Post by koiueo »

wongarsu wrote: post #496
Loeffelmann wrote: post #450

Earlier quoted context omitted.

If you ever work with LLMs you know that they quite frequently give up. Sometimes it's a // TODO: implement logic or a "this feature would require extensive logic and changes to the existing codebase". Sometimes they just declare their work done. Ignoring failing tests and builds. You can nudge them to keep going but I often feel like, when they behave like this, they are at their limit of what they can achieve.

If I tell it to implement something it will sometimes declare their work done before it's done. But if I give Claude Code a verifiable goal like making the unit tests pass it will work tirelessly until that goal is achieved. I don't always like the solution, but the tenacity everyone is talking about is there

> but the tenacity everyone is talking about is there

I always double-check if it doesn't simply exclude the failing test.

The last time I had this, I discovered it later in the process. When I pointed this out to the LLM, it responded, that it acknowledged thefact of ignoring the test in CLAUDE.md, and this is justified because [...]. In other words, "known issue, fuck off"

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

#544

Post by mlrtime »

chrisjj wrote: post #527
simonw wrote: post #503

Earlier quoted context omitted.

https://gisthost.github.io/?a41ce6304367e2ced59cd237c576b817... - which built https://github.com/datasette/datasette-transactions exactly the way I wanted it to be built

> exactly the way I wanted it to be built You verified each line?

What? Why would you want to?

See this is a perfect example of OPs statement! I don't care about the lines, I care about the output! It was never about the lines of code.

Your comment makes it very clear there are different viewpoints here. We care about problem->solution. You care about the actual code more than the solution.

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

#545

Post by audience_mem »

chrisjj wrote: post #531
audience_mem wrote: post #498

Earlier quoted context omitted.

Is this a joke? Are you genuinely implying that no one has ever got an LLM to write code that does exactly what they want?

No. Mashing up other peoples' code scraped from the web is not what I'd call writing code.

Can you not see how you truly, deep down, are afraid you might be wrong?

It's clouding your vision.

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

#546

Post by djeastm »

jedberg wrote: post #302

> You realize that stamina is a core bottleneck to work There has been a lot of research that shows that grit is far more correlated to success than intelligence. This is an interesting way to show something similar. AIs have endless grit (or at least as endless as your budget). They may outperform us simply because they don't ever get tired and give up. Full quote for context: Tenacity. It's so interesting to watch…

>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.

"Listen, and understand! That Terminator is out there! It can't be bargained with. It can't be reasoned with. It doesn't feel pity, or remorse, or fear. And it absolutely will not stop... ever, until you are dead!"

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

#548

Post by mlrtime »

ryanjshaw wrote: post #524
jedberg wrote: post #302

> You realize that stamina is a core bottleneck to work There has been a lot of research that shows that grit is far more correlated to success than intelligence. This is an interesting way to show something similar. AIs have endless grit (or at least as endless as your budget). They may outperform us simply because they don't ever get tired and give up. Full quote for context: Tenacity. It's so interesting to watch…

I realized a long time ago that I’m better at computer stuff not because I’m smarter but because I will sit there all day and night to figure something out while others will give up. I always thought that was my superpower in the job industry but now I’m not so sure if it will transfer to getting AI to do what I need done…

Same, I barely made it through Engineering school, but would stay up all night figuring out everything a computer could do (before the internet).

I did it because I enjoyed it, and still do. I just do it with LLMs now. There is more to figure out than ever before and things get created faster than I have time to understand them.

LLM should be enabling this, not making it more depressing.

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

#550

Post by mlrtime »

Loeffelmann wrote: post #450
jedberg wrote: post #302

> You realize that stamina is a core bottleneck to work There has been a lot of research that shows that grit is far more correlated to success than intelligence. This is an interesting way to show something similar. AIs have endless grit (or at least as endless as your budget). They may outperform us simply because they don't ever get tired and give up. Full quote for context: Tenacity. It's so interesting to watch…

If you ever work with LLMs you know that they quite frequently give up. Sometimes it's a // TODO: implement logic or a "this feature would require extensive logic and changes to the existing codebase". Sometimes they just declare their work done. Ignoring failing tests and builds. You can nudge them to keep going but I often feel like, when they behave like this, they are at their limit of what they can achieve.

Nope, not for me, unless I tell it to.

Context matters, for an LLM just like a person. When I wrote code I'd add TODOs because we cannot context switch to another problem we see every time.

But you can keep the agent fixated on the task AND have it create these TODOs, but ultimately it is your responsibility to find them and fix them (with another agent).

Post reply on HN