Live data from Hacker News

Claude Code on the web

anthropic.com

381–390 of 405 posts

Re: Claude Code on the web

#381
post #308

We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI. I'm doing massive lifts with it on software that would never before have been feasible for me personally, or any team I've ever run. I'll use Claude Code maybe once every two weeks as a second set of eyes to inspect code and document a bug, with mixed success. But my experience has been that initially Claude Co…

Feels like with every announcement there’s the same comment: “this LLM tool I’m using now is the real deal, the thing I was using previously and spending stupid amounts of money on looked good but failed at XYZ, this new thing is where it’s at”. Rinse and repeat. Which means it wasn’t true any of the previous times, so why would it be true this time? It feels like an endless loop of the “friendship ended” meme with A…

Because there is no switching cost, it's easy to switch, just change the API and be done

Re: Claude Code on the web

#382
post #348

Earlier quoted context omitted.

I'm like 80% sure Sonnet 4.5 is just rebranded Opus. Sonnet 4 was a coding companion, I could see what it was doing and it did what I asked. Sonnet 4.5 is like Opus, it generates massive amounts of "helper scripts" and "bootstrap scripts" and all kinds of useless markdown documentation files even for the tinies PoC scripts.

It's very much not, so I'm more than happy to take that bet - how much are we wagering? Have you ever used each for non-coding tasks? The generation of helper, markdown and bootstrap scripts are very dependent on your harness.

I paid for "Claude Code", I'm not asking it for stuff about the Mesopotamian empire :)

Re: Claude Code on the web

#383
post #308

We were heavy users of Claude Code ($70K+ spend per year) and have almost completely switched to codex CLI. I'm doing massive lifts with it on software that would never before have been feasible for me personally, or any team I've ever run. I'll use Claude Code maybe once every two weeks as a second set of eyes to inspect code and document a bug, with mixed success. But my experience has been that initially Claude Co…

Feels like with every announcement there’s the same comment: “this LLM tool I’m using now is the real deal, the thing I was using previously and spending stupid amounts of money on looked good but failed at XYZ, this new thing is where it’s at”. Rinse and repeat. Which means it wasn’t true any of the previous times, so why would it be true this time? It feels like an endless loop of the “friendship ended” meme with A…

Another way to look at it is it's very cut throat. Switching costs are low for now, by design. The ways to get you locked in haven't been developed.

Re: Claude Code on the web

#384
post #308

Earlier quoted context omitted.

Feels like with every announcement there’s the same comment: “this LLM tool I’m using now is the real deal, the thing I was using previously and spending stupid amounts of money on looked good but failed at XYZ, this new thing is where it’s at”. Rinse and repeat. Which means it wasn’t true any of the previous times, so why would it be true this time? It feels like an endless loop of the “friendship ended” meme with A…

Because there is no switching cost, it's easy to switch, just change the API and be done

With CLI tools like Claude code and codex cli there is some friction due to the change in user experience ie keyboard shortcuts, commands etc

Re: Claude Code on the web

#385
post #89

I feel like these background agents still aren't doing what I want from a developer experience perspective. Running in an inaccessible environment that pushes random things to branches that I then have to checkout locally doesn't feel great. AI coding should be tightly in the inner dev loop! PRs are a bad way to review and iterate on code. They are a last line of defense, not the primary way to develop. Give me an is…

Thank you. Every time these agentic cloud tools come out, I wonder to myself whether I'm not using them right or misunderstand vs, say, local Cursor development paradigm.

Plus they generate so much noise with all the extra commits and comments that go to everyone in slack and email rather than just me.

Re: Claude Code on the web

#386

Earlier quoted context omitted.

This is hilarious because for me Cursor with GPT-5 often generates Elixir that isn't even syntactically correct. It needs to be told not to use return statements, and not to try to index linked lists as arrays. Code is painfully non-idiomatic to the point of being borderline useless even in the simpler cases. Claude Sonnet 4.5 is marginally better, but not by much. Any ambitious overhaul, refactoring or large feature…

Try tidewave.ai, Jose made it (mcp thingy). Works well with GPT-5.

btw your website doesn't load

Re: Claude Code on the web

#387

Earlier quoted context omitted.

Actually, there are more internet users today than at any point in history. The internet is far from dead. The commenter in question is the CTO of the company which makes Wordfence. My instinct says they're not on the OpenAI payroll and you're looking at a normal comment and not advertisement. I think you should check your priors man; it's worth thinking critically before you toss out accusations like that.

Thanks joenot443. I suspect the only way to prove that I’m legit to the doubters is to do something a paid shill or a bot would never ever do. To the commenters who think I’m a shill or bot: fuck every single one of you and the various motherfucking horses you rode in on. I suspect we may be entering a dystopia where vulgarity is proof of life.

If it payed, shills and bots would use every slur under the sun without a shred of hesitation.

Re: Claude Code on the web

#388
post #196

Earlier quoted context omitted.

so hey by the way, have you discovered Wispr Flow or something similar so you can talk to your computer like Scotty does?

Yeah I've tried it a bit it's not a habit for me yet. I write code on my phone a lot using ChatGPT voice mode though!

Here's what I did to make voice (now WisprFlow, before Superwhisper) a habit:

  1. Install Karabiner-Elements, a free macOS keyboard remapper[0]
  2. Map F19 -> F5 (mic button) in Karabiner-Elements
  3. Choose F19 as the voice hotkey in your voice app
And now you can use the handy F5 mic button on your Apple keyboard. WisprFlow automatically has it set for:

  - press and hold to talk
  - double tap for indeterminate listening until you f5/esc
That workflow alone, of using the f5 key and switching between the two modes of speaking (holding or double-tap), has freed up a not insignificant part of my working memory. Turning abstract thoughts into text is higher cost than turning them into voice.

I predict individual offices[1] will be more popular as a choice for startups.

[0]: https://karabiner-elements.pqrs.org

[1]: https://queue.acm.org/detail.cfm?id=1281887

Re: Claude Code on the web

#389
post #196

Earlier quoted context omitted.

Yeah I've tried it a bit it's not a habit for me yet. I write code on my phone a lot using ChatGPT voice mode though!

Here's what I did to make voice (now WisprFlow, before Superwhisper) a habit: 1. Install Karabiner-Elements, a free macOS keyboard remapper[0] 2. Map F19 -> F5 (mic button) in Karabiner-Elements 3. Choose F19 as the voice hotkey in your voice app And now you can use the handy F5 mic button on your Apple keyboard. WisprFlow automatically has it set for: - press and hold to talk - double tap for indeterminate listening…

fwiw, I use the fn/international key at the bottom left of the keyboard. it's easier to locate and I (a privilege I enjoy because I rarely use diacritics) barely use it for anything else.
Post reply on HN