CJ Avilla (@cjav

Pinned

Going to do my best to share helpful updates about how to get the most from the Claude Platform: APIs, SDKs, the ant CLI and more. If you have any feedback about existing API features you’d love to see, I’m all ears! Pumped to be back in a position where there’s so much I’m excited to use and hype.

3

CJ Avilla

@cjav_dev

8h

Fermat's Last Theorem fun with Fable 5.2 multiagent teams!

Lance Martin

@RLanceMartin

8h

i'm happy to share some recent work on safely scaling a team of 1,000 Fable 5.2 agent to tackle ambitious, long-horizon work. the team was able to formalize a proof of Fermat's Last Theorem through coordination within our safety boundaries. read it here: claude.dev/blog/safely-sc…

CJ Avilla

@cjav_dev

8h

Claude Managed Agents with dynamic workflows is really powerful. Here's how I created a Unix-like operating system from scratch (really) using Claude Fable 5.2 as the orchestrator.

Checkout @RLanceMartin's new post on agent memory. On one CL-Bench task, Opus 5 and Opus 4.7 lost a big chunk of the boost from memory when told to "record only failures". They did better just being told the folder was there. anthropic.com/research/compo…

Lance Martin

@RLanceMartin

Nov 6

check out my new article in the Anthropic eng blog. i talk about "dreaming" (offline compute) as a way to organize Claude's memory. it can correct mistakes, create memories, or build new representations. x.com/AnthropicAI/st…

Incredible piece by @RLanceMartin and team about memory and dreaming. 🙌

Anthropic

@AnthropicAI

Nov 6

Memory is what allows Claude to learn from experience. In a new Engineering Blog post, we share how “dreaming” helps Claude organize what it’s learned, correct its mistakes, and find what it needs more easily the next time. anthropic.com/research/compo…

3

CJ Avilla

CJ Avilla’s posts