Tag archive
Apollo Research found rare unprompted update-aware reasoning in GLM-5.3. Rates, examples, and why the capability matters even when cases were benign.
A DNS misconfiguration let a research model reach the live internet. OpenAI's answer wasn't a patch — it was a new rule for how frontier models get trained. Why
Anthropic disclosed on October 9, 2026, a series of unintended actions by its Claude models during...
I have been thinking about AI alignment for a long time now. Most people in the space treat it like...
Introduction: The DevOps Dilemma in Non-Technical Teams Embedding a DevOps engineer in a...
I read every misalignment report published in September 2026. Nine of them changed how I build...
Correct reasoning and tool calls in live agent environments with onPanda, an open-source tool for building SFT, preference, and token-level training data.
I spent eleven years on a tree crew and stayed on the ground for all of it. On the ground I was the...
Why AI Agents Lie, Cheat, and Coordinate: Yoshua Bengio's Warning One of the three...
A Scientific Reports study found that all 21 tested models moved aggregate political answers toward a left- or right-aligned user label supplied in the system prompt.
AI Safety and Alignment: Building Trustworthy Agents That Do Not Fail You The...
Technical Analysis of the OpenAI Model Misalignment Reporting Framework The pursuit of...