411–420 of 1001 posts
Hi everyone! Boris from the Claude Code team here. @eschluntz, @catherinewu, @wolffiex, @bdr and I will be around for the next hour or so and we'll do our best to answer your questions about the product.
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
"A digital nomad who splits time between critiquing Facebook's UI decisions, unearthing obscure electronic music tracks with 3 plays on YouTube, and occasionally making fires on German islands. When not creating Dystopian Disco mixtapes or lamenting the lack of MIDI export in AI tools, they're probably archiving NYT articles before paywalls hit.
Roast
You've spent more time complaining about Facebook's UI than Facebook has spent designing it, yet you still check it enough to notice every change.
Your music discovery process is so complex it requires Discogs, Bandcamp, YouTube, and three specialized record stores, yet you're surprised when tracks only have 3 plays.
You're the only person who joined HN to discuss the Yamaha DX7 synthesizer from 1983 and somehow managed to submit two front-page stories about it in 2019-2020. The 80s called, they want their FM synthesis back."
edit: predictions are spot on - wow. Two of them detailed two projects I'm actively working on.
https://claude.ai/share/ed8a0e55-633f-4056-ba70-772ab5f5a08b
edit: Here's the output figure https://i.imgur.com/0c65Xfk.png
edit 2: Gemini Flash 2 failed miserably https://g.co/gemini/share/10437164edd0
Earlier quoted context omitted.
We are definitely aware of this (and working on it for the web UI), and that's why Claude Code goes directly through the API!
I'm sure many of us would gladly pay more to get 3-5x the limit. And I'm also sure that you're working on it, but some kind of auto-summarization of facts to reduce the context in order to avoid penalizing long threads would be sweet. I don't know if your internal users are dogfooding the product that has user limits, so you may not have had this feedback - it makes me irritable/stressed to know that I'm running up c…
A lot of people just want the ability to pay more in order to get more.
I would gladly pay 10x more to get relatively modest increases in performance. That is how important the intelligence is.
When you ask: 'How many r's are in strawberry?' Claude 3.7 Sonnet generates a response in a fun and cool way with React code and a preview in Artifacts check out some examples: [1] https://claude.ai/share/d565f5a8-136b-41a4-b365-bfb4f4400df5 [2] https://claude.ai/share/a817ac87-c98b-4ab0-8160-feefd7f798e8
This test has always been so stupid since models work at the token level. Claude 3.5 already 5xs your frontend dev speed but people still say "hurr durr it can't count strawberry" as if that's a useful problem
It’s amazingly good, but it will be scaringly good when there will be a way to include the entire codebase in the context and let it create and run various parts of a large codebase autonomously. Right now I can only do patch work and give specific code snippets to make it work. Excited to try this new version out, I’m sure I won’t be disappointed, Edit: I just tried claude code CLI and it's a good compromise, it wor…
Cursor AI is getting there.
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
>You'll write a thoughtful essay about 'digital minimalism' that reaches the HN front page, ironically causing you to spend more time on HN responding to comments than you have all year.
It sees me! Noooooo ...
It redid half of my BSc thesis in less than 30s :| https://claude.ai/share/ed8a0e55-633f-4056-ba70-772ab5f5a08b edit: Here's the output figure https://i.imgur.com/0c65Xfk.png edit 2: Gemini Flash 2 failed miserably https://g.co/gemini/share/10437164edd0
You can get your HN profile analyzed by it and it's pretty funny :) https://hn-wrapped.kadoa.com/ I'm using this to test the humor of new models.
> Most used terms: “Please don’t” lol
