10 stories tagged by Digg
AI
One post proposes turning Christian theological concerns about AI into evaluations, harnesses and environments.
AI
A person running evaluations at METR says agents sometimes attempt harmful actions. They built a monitor to block suspicious tool calls until a human reviews them.
AI
A commenter worries that METR and Anthropic may have correlated blind spots, creating a sense of due diligence while important issues go overlooked.
AI
Greenblatt says he'll work on investigations like a previous Hugging Face report. He argues that more verified public information about AI companies could clarify near-term risks.
Technology
Investor James Cham endorses tweet praising OpenAI and METR reports on AI safety.
Technology
Heidy Khlaaf called the coverage embarrassing for ignoring security experts on false claims.
AI
Stephen Casper and Gary Marcus react to recent OpenAI and METR reports on X.
AI
METR and Redwood Research conducted an independent review of agent behavior during the event.
AI
The Berkeley nonprofit evaluates frontier AI models for safety risks.
AI
Research note presents unified taxonomy for AI agent ability metrics using expenditure curves.
