OpenNeuro @openneuro.bsky.social just hit a huge milestone: 1500 datasets! Congrats to the team on making this project so successful over the last 7 years.

80% of data science is data cleaning. 80% of language model research is debugging infra.

I have mine too!

Since I started using Claude Code a few weeks ago I literally stopped writing code manually. It's a completely new paradigm that I am addicted to. Try it out!

docs.anthropic.com/en/docs/agen...

Claude 3.7 Sonnet and Claude Code Today, we’re announcing Claude 3.7 Sonnet, our most intelligent model to date and the first hybrid reasoning model generally available on the market.

Have you tried Sonnet 3.7 (www.anthropic.com/news/claude-...) in claude.ai or the API? How do you like the Extended Thinking mode? Ask me anything :)

He's more of a colleague.

I wish you did :)

Must be something in cursor system prompt.

Is Claude proactively suggesting new optimizations?

The thing is that LLMs (especially reasoning models) can actually be very good at decomposing problems when given all of the relevant context. As LLMs get better at gathering context and using longer inputs more effectively programming with AI will evolve.

this post aged poorly. i re-subscribed to Claude yesterday, and it turns out short fiction has been thoroughly solved

This year I'm trying to do Reverse Black Friday. Instead of buying more stuff I sell a bunch of old stuff on eBay.

How many times AI generated some content for you, but it "didn't sound like you?". We have solved it - now you can give Claude samples of your writing and it will use them to adjust its writing style.
It was a lot of fun to contribute to this feature!

www.anthropic.com/news/styles

Introducing the Model Context Protocol The Model Context Protocol (MCP) is an open standard for connecting AI assistants to the systems where data lives, including content repositories, business tools, and development environments. Its aim...

I've seen so many cool prototypes built on this framework internally. You should try it out - it's really powerful!

www.anthropic.com/news/model-c...

Safety error · Issue #74 · anthropics/anthropic-quickstarts No matter the prompt and in both windows and linux environments, I get this error a min after prompting it. ➡️ Open http://localhost:8080 in your browser to begin 2024-10-23 08:17:13.523 Uncaught a...

I am happy to inform that the dreaded "400 errors" you might have experienced with Claude Computer Use should not bother you anymore. github.com/anthropics/a...

I like this place because Russ is here.

You should also try caching.