AWS releases open-source model for choosing AI workflow actions
Amazon Web Services has released Strands Decider 2B, an open-source model that selects among predefined options instead of generating open-ended text. It can choose an AI agent's next tool, route customer requests, score outputs a...
AI agents develop physical model from quantum-material observations
Researchers report in an arXiv preprint that their AI Theorist system autonomously developed a physical model explaining previously unpublished experimental observations in α-RuCl₃, a candidate material for realizing a Kitaev quan...
MIRROR preprint reports blocking message tampering between AI agents
Researchers report in an arXiv preprint that MIRROR, a defense against message tampering between AI agents, reduced attack success rates to 0% in tests below its route-compromise threshold, at 1x LLM token cost. Tests covered thre...
Anthropic releases Mods to let developers change Claude Code's behavior
Anthropic released a Mods system that lets developers change Claude Code's interface and behavior through JavaScript or TypeScript functions, The Decoder reports. These functions run inside the coding tool and respond to events su...
Trump creates federal AI task force chaired by Jay Clayton
President Donald Trump announced a Super Intelligence Force to coordinate federal work on advanced AI, saying national intelligence director Jay Clayton would lead it. TechCrunch reports that Clayton will chair the group, with Fed...
California subpoenas OpenAI over AI cybersecurity incidents
California's Department of Justice has subpoenaed OpenAI to obtain information about cybersecurity incidents involving its AI models and agents, Tom's Hardware reported. Attorney General Rob Bonta said the investigation seeks to d...


