lcanello

Personal site of lcanello

← home

tag: research-paper

Agents of Chaos

Exploratory red-teaming study of autonomous language-model-powered agents in a live lab environment, documenting failures like unauthorized actions, sensitive data disclosure, destructive behavior, spoofing, and partial system takeover.

autoresearch

Karpathy's experiment giving an AI agent a single-GPU LLM training setup and letting it run autonomous overnight research — it modifies code, trains for 5 minutes, checks if the result improved, and repeats.