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

Claude 3.7 Sonnet and Claude Code

anthropic.com

Post reply on HN
Print view View original

551–560 of 1001 posts

Re: Claude 3.7 Sonnet and Claude Code

#551

Post by bt1a »

bearjaws wrote: post #347
anotherpaulg wrote: post #331

Claude 3.7 Sonnet scored 60.4% on the aider polyglot leaderboard [0], WITHOUT USING THINKING. Tied for 3rd place with o3-mini-high. Sonnet 3.7 has the highest non-thinking score, taking that title from Sonnet 3.5. Aider 0.75.0 is out with support for 3.7 Sonnet [1]. Thinking support and thinking benchmark results coming soon. [0] https://aider.chat/docs/leaderboards/ [1] https://aider.chat/HISTORY.html#aider-v0750

Thanks for all the work on aider, my favorite AI tool.

It really is best in slot. Owe it to git, which has a particular synergy with a hallucination-prone but correctable system

Re: Claude 3.7 Sonnet and Claude Code

#552

Post by seunosewa »

swairshah wrote: post #342
bcherny wrote: post #91

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.

Why not just open source Claude Code? people have tried to reverse eng the minified version https://gist.githubusercontent.com/1rgs/e4e13ac9aba301bcec28...

Claude Code is on github: https://github.com/anthropics/claude-code

Re: Claude 3.7 Sonnet and Claude Code

#553

Post by sheepdestroyer »

anotherpaulg wrote: post #331

Claude 3.7 Sonnet scored 60.4% on the aider polyglot leaderboard [0], WITHOUT USING THINKING. Tied for 3rd place with o3-mini-high. Sonnet 3.7 has the highest non-thinking score, taking that title from Sonnet 3.5. Aider 0.75.0 is out with support for 3.7 Sonnet [1]. Thinking support and thinking benchmark results coming soon. [0] https://aider.chat/docs/leaderboards/ [1] https://aider.chat/HISTORY.html#aider-v0750

Nice !

Could we please get benchmarks for architect / DeepSeek R1 + claude-3-7-20250219 ?

To compare perf and price with Sonnet-3.7-thinking

Re: Claude 3.7 Sonnet and Claude Code

#554

Post by WatchDog »

gwd wrote: post #448
anotherpaulg wrote: post #331

Claude 3.7 Sonnet scored 60.4% on the aider polyglot leaderboard [0], WITHOUT USING THINKING. Tied for 3rd place with o3-mini-high. Sonnet 3.7 has the highest non-thinking score, taking that title from Sonnet 3.5. Aider 0.75.0 is out with support for 3.7 Sonnet [1]. Thinking support and thinking benchmark results coming soon. [0] https://aider.chat/docs/leaderboards/ [1] https://aider.chat/HISTORY.html#aider-v0750

Interesting that the "correct diff format" score went from 99.6% with Claude 3.5 to 93.3% for Claude 3.7. My experience with using claude-code was that it consistently required several tries to get the right diff. Hopefully all that will improve as they get things ironed out.

3.7 completed a lot more than 3.5, without seeing the actual results, we can't tell if there were any regressions in the edit format among the previously completed tasks.

Re: Claude 3.7 Sonnet and Claude Code

#555

Post by unsupp0rted »

nomel wrote: post #548
unsupp0rted wrote: post #478

Anybody else noticing that in Cursor, Claude Sonnet 3.7 is thinking much slower than Claude Sonnet 3.5 did?

Claude 3.5 was not a thinking model. It's thinking time was 0s.

Okay, if we're being pedantic, then anybody notice 3.7 (not 3.7 thinking) is slower to respond and slower to make code changes than 3.5 was?

Re: Claude 3.7 Sonnet and Claude Code

#556

Post by edmundsauto »

clangfan wrote: post #186
pookieinc wrote: post #108

Earlier quoted context omitted.

The biggest complaint I (and several others) have is that we continuously hit the limit via the UI after even just a few intensive queries. Of course, we can use the console API, but then we lose ability to have things like Projects, etc. Do you foresee these limitations increasing anytime soon? Quick Edit: Just wanted to also say thank you for all your hard work, Claude has been phenomenal.

this is also my problem, ive only used the UI with $20 subscription, can I use the same subscription to use the cli? I'm afraid its like those aws api billing where there is no limit to how much I can use then get a surprise bill

I use AnythingLLM so you can still have a "Projects" like RAG.

Re: Claude 3.7 Sonnet and Claude Code

#557

Post by hectormalot »

epistasis wrote: post #457
epistasis wrote: post #261

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…

Update: Code tokens appear to be cheaper than 3.7 tokens, looks like it is around $0.75/million tokens for code, rather than the $3/million that the articles specifies for Claude 3.7

Likely because it is blended with cached token pricing, which is at $0.30/million. You can use ‘group by’ in the usage portal to see the breakdown.

Re: Claude 3.7 Sonnet and Claude Code

#558

Post by scubbo »

LouisSayers wrote: post #178
eschluntz wrote: post #140

Earlier quoted context omitted.

hi! I've been working on demos where I let Claude Code run for hours at a time on a sandboxed project: https://x.com/ErikSchluntz/status/1894104265817284770 TLDR: asking claude to speed up my code once 1.8x'd perf, but putting it in a loop telling it to make it faster for 2 hours led to a 500x speedup!

I assume you had a comprehensive test suite?

Lol, good one.

Re: Claude 3.7 Sonnet and Claude Code

#559

Post by frohrer »

sha16 wrote: post #504
bcherny wrote: post #91

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.

When I first started using Cursor the default behavior was for Claude to make a suggestion in the chat, and if the user agreed with it, they could click apply or cut and paste the part of it they wanted to use in their larger project. Now it seems the default behavior is for Claude to start writing files to the current working directory without regard for app structure or context (e.g., config files that are defined…

Cursor has two LLM interaction modes, chat and composer. The chat does what you described first and composer can create/edit/delete files directly. Have you checked which mode you're on? It should be a tab above your chat window.

Re: Claude 3.7 Sonnet and Claude Code

#560

Post by trees101 »

bcherny wrote: post #221
Flux159 wrote: post #166

Earlier quoted context omitted.

Is there a way to always accept certain commands across sessions? Specifically for things like reading or updating files I don't want to have to approve that each time I open a new repl. Also, is there a way to switch models between 3.5-sonnet and 3.5-sonnet-thinking? Got the initial impression that the thinking model is using an excessive amount of tokens on first use.

When you are prompted to accept a bash command, we should be giving you the option to not ask again. If you're not seeing that for a specific bash command, would you mind running /bug or filing an issue on Github? https://github.com/anthropics/claude-code/issues Thinking and not thinking is actually the same model! The model thinks automatically when you ask it to. If you don't explicitly ask it to think, it won't us…

with Claude coder, how does history work? I used it with my account, ran out of credit then switched to a work account but there was no chat history or other saved context of the work that had been done. I logged back in with my account to try copy it but it was gone.
Post reply on HN