Well, the tokenizer I used was trained on large quantities of data — I filtered the tokens based on yet more data from FineWeb. Question is if that's acceptable according to your rules…
CODE
-
Building with Codex: Sharing Feedback and Excitement
By
–
Amazing! Please share feedback as you start building with Codex, excited to hear how it goes!
-
Windsurf launches AI-assisted Codemaps
By
–
Windsurf has launched AI-assisted Codemaps to help navigate through the codebase structure and visualise code objects. https://t.co/h30hIEINAL pic.twitter.com/nndaiGTQ6z
— 🚨 AI News | TestingCatalog (@testingcatalog) 5 novembre 2025Windsurf has launched AI-assisted Codemaps to help navigate through the codebase structure and visualise code objects.
-
Celebrating shift from JSON tool calls to code blobs
By
–
Finally! Congrats, a step in a great direction!
We've been stuck in this local optimum of "writing actions as JSON blobs with individual tool calls in them" for much too long. Just let models write tool calls in code blobs! -
Retokenization and Language Knowledge in Model Training
By
–
The biggest question is whether you allow re-tokenization, and whether that should be done with the same data as the training itself. Right now there is knowledge about the language in existing tokens built-in and changing that is against the rules and/or unfavorable.
-
Rediscovery of CodeAct and smolagents a year later
By
–
I think they're finally going to rediscover CodeAct and smolagents, 1 year later!
-
MCP Large Data Implementation in Production at Lutra.ai
By
–
I wrote about this much earlier: https://
jngiam.bearblog.dev/mcp-large-data/ and we implemented it in production at http://
Lutra.ai – we would appreciate some mention of our work too. It was also on HN front page for more than a day – well distributed! -
Building Efficient AI Agents with Model Context Protocol
By
–
New on the Anthropic Engineering blog: tips on how to build more efficient agents that handle more tools while using fewer tokens. Code execution with the Model Context Protocol (MCP):
-
Autonomous AI Through Dynamic Model Synthesis and Self-Improving Abstractions
By
–
The path to autonomous AI is a system that learns to solve new problems by synthesizing models of them on the fly (as code), and that gets smarter over time by adding new abstractions to its own library (also as code), compounding its capabilities. Not a static map — rather, an
-
Codex CLI Pull Requests Growth Compared to Gemini CLI
By
–
Counting PRs is a little silly, but there's a huge shift in the Codex CLI PRs since August – though still behind Gemini CLI PRs, which I did not expect. New Codex model would be pretty cool to have.