This is Claude Sonnet 4.6: our most capable Sonnet model yet.
It’s a full upgrade across coding, computer use, long-context reasoning, agent planning, knowledge work, and design.
It also features a 1M token context window in beta.
@ziwenxu_ Did an M2 Pro 16gb instead of the M4 32gb. Locally running qwen3:8b and working like a charm. Interested in running Minimax. Currently on Claude API (to avoid getting banned). Experimentation will make the eco much better. Thanks for sharing.
@jordymaui Thanks! I think my Claw got messed up in the process and I have half a GUI and some errors here and there. Might reinstall/update to get it going. Using qwen3:8b + Claude
Just ordered some @stripepress books to dive into. Then, I'll be printing (following instructions) some papers @MattPRD recommend here: https://t.co/9C1i2heIye
Rules, commands, MCP servers, subagents, modes, hooks, skills...
There's a lot of stuff! And tbh it's a little confusing.
Here's what you need to know (and how we got here).
Here's my enormous round-up of everything we learned about LLMs in 2025 - the third in my annual series of reviews of the past twelve months
https://t.co/HD9Zf85SG2
This year it's divided into 26 sections! This is the table of contents: