Google's new multi-agent system turns messy wearable sensor streams into statistically vetted biomarker candidates through adversarial validation and human review.
SkyRL's IsoExec makes vLLM rollout and Megatron training agree bitwise on token log-probabilities, cutting numerical drift below 1e-6 with 25% overhead.
Runway's new Ruby model upconverts standard dynamic range footage to true 16-bit HDR in ProRes and EXR, targeting professional post-production pipelines.
Artificial Analysis launched a blind human-preference leaderboard for voice agents, and the model users like most is not the one that finishes the task.
TrueFoundry open-sourced TrueForge, an MIT-licensed agent runtime that ran 30-75% cheaper than Claude Managed Agents on a 14-task enterprise benchmark.
DeepSeek open-sourced dsh, a plugin-based coding agent framework where the model, tools, sandbox, UI, and even the agent loop itself are all swappable.
A new agent skill turns a single reference image into diffable TypeScript that procedurally reconstructs the object as an animation-ready Three.js scene.
Hugging Face released Tau, an MIT-licensed terminal coding agent designed as much for reading as running, with a three-layer architecture you can actually understand.
A Go-based open source relay platform pools Claude, OpenAI, Gemini, and Grok subscriptions behind one endpoint with billing, sticky sessions, and cost sharing.