Christopher Berry

This week: Weight pruning, safety neurons, political neutrality, novelty evaluation, neuron personas, anthropic IPO.

This week: Hiding capabilities, measuring consensus in agent networks, entertain then cancel, PELE, company world models, kill switch, base optimization,

This Week: Hardwired pause, the geopolitical trap, neural networks are already clean, AI enhance or erode expertise, human-AI collaboration, empowering dictators, tiny little office.

This week: Self-play, context language models, santa clause, employee disclosure with AI, influence and binding.

This week: Reliability theory for AI Control, auditing sabotage bench, autobenchmark, optimal timing for superintelligence, serious AI product.

This week: Debunkable beliefs, pain responses in llm’s, AI changing labour demand, physical capabilities, MoE as efficient retrievers

This week: Reliable weak-to-strong monitoring, corrupt plans, stellar colosseum, cognitive virus, new polling, Whoopi.

This week: Mechanism design for alignment and control, you are what you read, cheating and whistleblowing in autonomous research swarms, confidence shortcut, course design in the age of AI.

This week: If God Arrived As a Chatbot, Late-Stage Pressure States in Long-Horizon Tool-Use Agents, AI Control safety case, Questionnaire, The Coming Storm

This week: METR’s brief independent investigation of agents’ behavior, The Hugging Face incident, Breaking ArrowCloak, Prime Agent, maturation process