Meet the people behind the posts.

Chris Olah

Anthropic co-founder and interpretability researcher

@ch402

Studies the internal features and circuits of neural networks, connecting visual explanations to experiments on why a particular model produces a particular response.

Johann Rehberger

AI security researcher; author of Embrace The Red

@wunderwuzzi23

Investigates how instructions hidden in webpages, code and tool responses can redirect AI agents, with concrete attack reports and the permissions that made them possible.

Kai Greshake

AI security researcher at NVIDIA

@KGreshake

Explains indirect prompt injection: an attacker places instructions in material an AI application retrieves, then uses the application’s capabilities to influence its behavior.

Lilian Weng

Machine learning researcher; author of Lil’Log

@lilianweng

Connects reasoning and reinforcement learning methods to their failure modes, including models that improve an evaluator's score without completing the intended task.

Neel Nanda

Google DeepMind mechanistic interpretability team lead

@NeelNanda5

Explains how to inspect and intervene on model internals, separating a useful hypothesis about a mechanism from evidence that a causal test supports it.

Simon Willison

Independent developer; creator of Datasette and LLM

@simonw

Turns experiments with coding agents into explanations of what to build, how to inspect the result and how to keep learning from code a model wrote.

Stella Biderman

AI researcher and executive director of EleutherAI

@BlancheMinerva

Studies how model behavior develops during training, using public checkpoints and controlled experiments on memorization and capabilities.