261–270 of 1001 posts
After initialization it was up to 500k tokens ($1.50). After a few questions and a small edit, I'm up to over a million tokens (>$3.00). Not sure if the amount of code navigation and typing saved will justify the expense yet. It'll take a bit more experimentation.
In any case, the default API buy of $5 seems woefully low to explore this tool.
Earlier quoted context omitted.
This is BS and you are not listening and watching carefully.
OK then show me a model that can answer honestly and correctly about whether or not it knows something.
It's pretty fascinating to refresh the usage page on the API site while working [0]. After initialization it was up to 500k tokens ($1.50). After a few questions and a small edit, I'm up to over a million tokens (>$3.00). Not sure if the amount of code navigation and typing saved will justify the expense yet. It'll take a bit more experimentation. In any case, the default API buy of $5 seems woefully low to explore t…
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.
One of the silver bullets of Claude, in the context of coding, is that it does NOT use RAG when you use it via the web interface. Sure, you burn your tokens but the model sees everything and this let it reply in a much better way. Is Claude Code doing the same and just doing document-level RAG, so that if a document is relevant and if it fits , all the document will be put inside the context window? I really hope so!…
Earlier quoted context omitted.
Seems broken? Getting > An error occurred in the Server Components render. The specific message is omitted in production builds to avoid leaking sensitive details. A digest property is included on this error instance which may provide additional details about the nature of the error.
Worked for me, seems to be case sensitive (?) I'll post these incase I just got lucky and it still doesn't work for you. https://hn-wrapped.kadoa.com/Philpax?share > You explain WebAssembly memory management with such passion that we're worried you might be dating your pointer allocations. > Your comments about multiplayer game architecture are so detailed, we suspect you've spent more time debugging network code tha…
Yes, I'm quite the eclectic kind!
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.
Thanks for this - exciting launch. Do you have examples of cool applications or demos that the HN crowd should check out?
Not OP obviously, but I've built so many applications with Claude, here are just a few:
[1]
Mockup of Utopian infrastructure support button (this is just a mockup, the buttons don't do anything): https://claude.site/artifacts/435290a1-20c4-4b9b-8731-67f5d8...
[2]
Robot body simulation: https://claude.site/artifacts/6ffd3a73-43d6-4bdb-9e08-02901d...
[3]
15-piece slider puzzle: https://claude.site/artifacts/4504269b-69e3-4b76-823f-d55b3e...
[4]
Canada joining the U.S., checklist: https://claude.site/artifacts/6e249e38-f891-4aad-bb47-2d0c81...
[5]
Secure encryption and decryption with AES-256-GCM with password-based key derivation:
https://claude.site/artifacts/cb0ac898-e5ad-42cf-a961-3c4bf8...
(Try to decrypt this message
kFIxcBVRi2bZVGcIiQ7nnS0qZ+Y+1tlZkEtAD88MuNsfCUZcr6ujaz/mtbEDsLOquP4MZiKcGeTpBbXnwvSLLbA/a2uq4QgM7oJfnNakMmGAAtJ1UX8qzA5qMh7b5gze32S5c8OpsJ8=
With the password "Hello Hacker News!!" (without quotation marks))
[6]
Supply-demand visualizer under tariffs and subsidies: https://claude.site/artifacts/455fe568-27e5-4239-afa4-051652...
[7]
fortune cookie program: https://claude.site/artifacts/d7cfa4ae-6946-47af-b538-e6f992...
[8]
Household security training for classified household members (includes self-assessment and certificate): https://claude.site/artifacts/7754dae3-a095-4f02-b4d3-26f1a5...
[9]
public service accountability training program: https://claude.site/artifacts/b89a69fb-1e46-4b5c-9e96-2c29dd...
[10]
Nuclear non-proliferation "big brother" agent technical demonstration: https://claude.site/artifacts/555d57ba-6b0e-41a1-ad26-7c90ca...
Dating stuff:
[11]
Dating help: Interest Level Assessment Game (is she interested?) https://claude.site/artifacts/523c935c-274e-4efa-8480-1e09e9...
[12]
Dating checklist: https://claude.site/artifacts/10bf8bea-36d5-407d-908a-c1e156...
Earlier quoted context omitted.
This is BS and you are not listening and watching carefully.
Even the best LLMs today are just junior devs with a lot of knowledge. They make a lot of the same mistakes junior devs would do. Even the responses, when you point out those mistakes, are the same. If anything, it's a tool for junior devs to get better and spend more time on the architecture. Using AI code without fully understanding it (ie operated by a non-programmer) is just recipe for disaster.
"You're right, but I just like wasting your time"
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.
How is your largest customer, Cursor, taking the news that you'll be competing directly with them?
Kagi LLM benchmark updated with general purpose and thinking mode for Sonnet 3.7. https://help.kagi.com/kagi/ai/llm-benchmark.html Appears to be second most capable general purpose LLM we tried (second to gemini 2.0 pro, in front of gpt-4o). Less impressive in thinking mode, about at the same level as o1-mini and o3-mini (with 8192 token thinking budget). Overall a very nice update, you get higher quality and higher…