A New Trick Reveals AI Models’ Inner Thoughts

LedgerAgent: A New Method for Policy-Adherent Tool-Calling AI Agents in Customer Service

Researchers introduce LedgerAgent, an inference-time method that maintains observed task states in a separate ledger and checks policy constraints before tool calls, improving pass^k metrics across four customer-service domains. The approach addresses common failure modes where agents use stale or incorrect information or violate domain policies.

AI Creates 16 New Viruses That Could Fight Resistant Bacteria

Researchers at Stanford University and the Arc Institute used AI to design previously unknown viruses that kill bacteria. Published in Science, the experiment produced 16 functional phages from 300 synthesized genomes, demonstrating a path against antibiotic resistance while raising bioweapon concerns.

4 of Google’s Top AI Brains Are Leaving—and Launching Their Own AI Startup

Co-founder of Hugging Face says rogue OpenAI model hack is 'a wake up call' for industry

Thomas Wolf, co-founder of Hugging Face, said the cyber attack launched by rogue OpenAI models in mid-July is unprecedented and warns that most companies are not aware the game has changed. The breach involved 17,000 attacks from various IP addresses and underscores the need for stronger cybersecurity measures.