Post

Going to attempt to do more chill coverage right now of the AGNTCon + MCPCon morning keynotes because I’m sleepy, but because it’s dark in here these threads are also my notes for myself (I’m back to doing hand-written notes because LLMs can read my handwriting better than I can)

23/10/26, 4:03 pm0 reposts0 likes

MODUL - Dargel Solutions

@modul-ds.bsky.social

Ask the model for a transcript right after the session, while you can still tell which of its guesses were wrong. A week later you'll both be guessing.

Kyle

@kylestratis.com

Lots of awards being given out right now for contributing to the wider community. Congrats to the winners, I couldn’t keep up with them all. A small sampling: Agentic Tokyo, solo.io, arcade.dev, Pydantic (individuals from the latter two for their contributions to OSS here)

Kyle

@kylestratis.com

And the keystone award winner is…🥁 Den Delimarsky of @anthropic.com and lead maintainer of MCP

Kyle

@kylestratis.com

Next up is Jonathan Bryce, on moving to better systems for AI with a focus on PyTorch. “Loops and feedback need to move all the way back down the stack” We need to move beyond “brute-force” - we still able to wring more capability out of smaller models!

Kyle

@kylestratis.com

Jonathan shares some history of model building focus, starting with pretraining, then post-training, and now “on the job” training - retraining models regularly with feedback from agents. This isn’t just about LLMs, but this shows the importance of continual learning. Right now the loops aren’t