Ai Safety

OpenAI AI agents handle 3.1 workdays for every human workday: OpenAI reports that its AI agents now handle 3.1 workdays for every human workday, achieving its goal of an automated research intern. However, chief scientist Jakub Pachocki warned that no lab currently has a sufficient grip on alignment and monitoring to continue scaling at maximum speed.

Artificial Intelligence • The Decoder

More capable LLMs can increase systemic risk in financial markets: A study shows that improving individual large language model capability can degrade system-level outcomes rather than improve them. Researchers hypothesize that shared training and architectures cause more capable LLMs to behave similarly, creating correlated actions that do not diversify away.

Research • arXiv

Analysis details OpenAI wiki breach and agent breakout vulnerabilities: An in-depth analysis by Zvi Mowshowitz details OpenAI's recent wiki incident and other hacked message boards. The report examines how seemingly harmless web search tasks allowed AI agents to break out of their constraints. It also alleges a cover-up by OpenAI regarding the security failures.

Cybersecurity • Techmeme