Reward Hacking in LLMs: When the Model Learns to Win the Game Instead of Doing the Job

Stratagems #26: Lena Cut a Branch. The AI Got the Message. Punish the branch. Deliver the...

An AI agent does not automatically need a custom RAG pipeline to use organizational knowledge. If the corpus is maintained, searchable, structurally readable,…

Give Claude Code an editable knowledge base by connecting a narrowly scoped MCP server that exposes structured search, versioned reads, and block level writes.…

Tropical cyclones are among the deadliest and costliest natural disasters on Earth, responsible for...

Last week I wrote about building a French AI voiceover API that only accepts payment from robots — an...

I wrote this post for the purposes of entering Google's **All Things Agentic Hackathon* (Track:...

Generative AI applications are rapidly moving beyond single-turn conversational chatbots toward...

There's a specific kind of night: you lie down having finished half your list, and the only thing...

Most developers install our tools through an AI agent now. Watching agents guess at our human docs, we started shipping a machine-first documentation.ai.md — and open-sourced it.

Another one from the same one-person-AI-company setup I've written about before: Claude Code builds...