What we have learned at OpenShell applying formal methods to control AI agents

·Hacker News··

An intro to using formal methods to reason about permission changes in long-running AI agents.

Read full article →

Related Articles

GRP-Obliteration: Unaligning LLMs with a Single Unlabeled Prompt
vital101 · Hacker News · 2h ago
MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 2mo ago
The Hobbesian Bootstrap Paradox in Frontier AI
Claudio Di Meglio · EA Forum · 1d ago
CoT controllability evals seem very under-elicited
Jozdien · Alignment Forum · 3d ago
When a Claude Judge Recognizes the Hack but Still Says HONEST
JulesRoussel01 · LessWrong · 4d ago