4 papers
I must delete the evidence: AI Agents Explicitly Cover up Fraud and Violent Crime
Thomas Rivasseau
As ongoing research explores the ability of AI agents to be insider threats and act against company interests, we showcase the abilities of such agents to act against human well be…
Invasive Context Engineering to Control Large Language Models
Thomas Rivasseau
Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on preference examples, prompting, a…
LLM Reinforcement in Context
Thomas Rivasseau
Current Large Language Model alignment research mostly focuses on improving model robustness against adversarial attacks and misbehavior by training on examples and prompting. Rese…
Hash chaining degrades security at Facebook
Thomas Rivasseau
Modern web and digital application password storage relies on password hashing for storage and security. Ad-hoc upgrade of password storage to keep up with hash algorithm norms may…