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

181–190 of 870 posts

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

#181

Post by mikkupikku »

testaccount28 wrote: post #129
charcircuit wrote: post #123

Earlier quoted context omitted.

You are using it wrong, or are using a weak model if your failure rate is over 50%. My experience is nothing like this. It very consistently works for me. Maybe there is a <5% chance it takes the wrong approach, but you can quickly steer it in the right direction.

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

I think a lot of it comes down to how well the user understands the problem, because that determines the quality of instructions and feedback given to the LLM.

For instance, I know some people have had success with getting claude to do game development. I have never bothered to learn much of anything about game development, but have been trying to get claude to do the work for me. Unsuccessful. It works for people who understand the problem domain, but not for those who don't. That's my theory.

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

#182

Post by bflesch »

simonw wrote: post #132
bluGill wrote: post #113

Earlier quoted context omitted.

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…

Have you tried showing it a copy of your coding standards? I also find pointing it to an existing folder full of code that conforms to certain standards can work really well.

Yeah let's share all your IP for the vague promise that it will somehow work ;)

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

#183

Post by ipaddr »

groby_b wrote: post #130
peaseagee wrote: post #101

Earlier quoted context omitted.

That's not true. Many technologies get more expensive over time, as labor gets more expensive or as certain skills fall by the wayside, not everything is mass market. Have you tried getting a grandfather clock repaired lately?

No. You don't get to make "technology gets more expensive over time" statements for deprecated technologies. Getting a bespoke flintstone axe is also pretty expensive, and has also absolutely no relevance to modern life. These discussions must, if they are to be useful, center in a population experience, not in unique personal moments.

I purchased a 5T drive in 2019 and the price is higher now despite newer better drives going on the market since.

Not much has down in price over the last few years.

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

#184

Post by wvenable »

daxfohl wrote: post #88
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…

I still find in these instances there's at least a 50% chance it has taken a shortcut somewhere: created a new, bigger bug in something that just happened not to have a unit test covering it, or broke an "implicit" requirement that was so obvious to any reasonable human that nobody thought to document it. These can be subtle because you're not looking for them, because no human would ever think to do such a thing. Th…

> These can be subtle because you're not looking for them

After any agent run, I'm always looking the git comparison between the new version and the previous one. This helps catch things that you might otherwise not notice.

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

#185

Post by bflesch »

maxdo wrote: post #36
vibeprofessor wrote: post #12

The AGI vibes with Claude Code are real, but the micromanagement tax is heavy. I spend most of my time babysitting agents. I expect interviews will evolve into "build project X with an LLM while we watch" and audit of agent specs

I've been doing vibe code interviews for nearly a year now. Most people are surprisingly bad with AI tools. We specifically ask them to bring their preferred tool, yet 20–30% still just copy-paste code from ChatGPT. fun stats: corelation is real, people who were good at vibe code, also had offer(s) with other companies that didn't run vibe code interviews.

Interesting you say that, feels like when people were too stupid to google things and "googling something" was a skill that some had and others didn't.

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

#186

Post by ipaddr »

arthurbrown wrote: post #174
groby_b wrote: post #130

Earlier quoted context omitted.

No. You don't get to make "technology gets more expensive over time" statements for deprecated technologies. Getting a bespoke flintstone axe is also pretty expensive, and has also absolutely no relevance to modern life. These discussions must, if they are to be useful, center in a population experience, not in unique personal moments.

Bought any RAM lately? Phone? GPU in the last decade?

The latest iphone has gone down in price? It's double. I guess the marketing is working.

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

#187

Post by fooker »

ipaddr wrote: post #173
simianwords wrote: post #109

Earlier quoted context omitted.

"repairing a unique clock" getting costlier doesn't mean technology hasn't gotten cheaper. check out whether clocks have gotten cheaper in general. the answer is that it has. there is no economy of scale here in repairing a single clock. its not relevant to bring it up here.

Clocks prices have gone up since 2020. Unless a cheaper better way to make clocks has emerged inflation causes prices to grow.

Luxury watches have gone up, 'clocks' as a technology is cheaper than ever.

You can buy one for 90 cents on temu.

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

#188

Post by rob »

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…

I've been playing around with the "Superpowers" [0] plugin in Claude Code on a new small project and really like it. Simple enough to understand quickly by reading the GitHub repo and seems to improve the output quality of my projects.

There's basically a "brainstorm" /slash command that you go back and forth with, and it places what you came up with in docs/plans/YYYY-MM-DD--design.md.

Then you can run a "write-plan" /slash command on the docs/plans/YYYY-MM-DD--design.md file, and it'll give you a docs/plans/YYYY-MM-DD--implementation.md file that you can then feed to the "execute-plan" /slash command, where it breaks everything down into batches, tasks, etc, and actually implements everything (so three /slash commands total.)

There's also "GET SHIT DONE" (GSD) [1] that I want to look at, but at first glance it seems to be a bit more involved than Superpowers with more commands. Maybe it'd be better for larger projects.

[0] https://github.com/obra/superpowers

[1] https://github.com/glittercowboy/get-shit-done

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

#189

Post by simianwords »

fooker wrote: post #171
techpression wrote: post #148

Earlier quoted context omitted.

The chart shows that they’re right though. Newer models cost more than older models. Sure they’re better but that’s moot if older models are not available or can’t solve the problem they’re tasked with.

OpenAI has always priced newer models lower than older ones.

not true! 4o was costlier than 3.5 turbo

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

#190

Post by simianwords »

ipaddr wrote: post #173
simianwords wrote: post #109

Earlier quoted context omitted.

"repairing a unique clock" getting costlier doesn't mean technology hasn't gotten cheaper. check out whether clocks have gotten cheaper in general. the answer is that it has. there is no economy of scale here in repairing a single clock. its not relevant to bring it up here.

Clocks prices have gone up since 2020. Unless a cheaper better way to make clocks has emerged inflation causes prices to grow.

not true, clocks have gone down after accounting for inflation. verified using ChatGPT.
Post reply on HN