Compare 11 open-source agent harnesses for local LLMs, including OpenCode, Pi, Goose, Cline, OpenHands, Aider, and Codex CLI.
Anthropic redesigned Claude Code Projects: a coordinator splits work into parallel cloud threads, beta on Pro and Max.
OpenAI's framework sets tracks and deadlines for disclosing model misalignment, launching with 6 reports from RL training ...
Microsoft open-sourced TauGrid, an MIT-licensed Kubernetes stack bundling tau CLI, Kueue queueing and GPU health monitoring.
Nunchux AI's training-free VC-Attention fixes value outliers and FP32 softmax bottleneck, speeding video DiT attention up to ...
Google Research's Retrieve-for-Train uses RL once to train a 53.9M-parameter diffusion retriever, delivering 12× to 20× ...
Stanford's Paper2Agent turns research papers into tested MCP servers, letting AI agents run their methods through natural ...
Prior Labs' TabPFN-3.5 beats the 2015 Otto winner with default settings and ranks first on 7 tabular benchmarks.
Google launches Gemini 3.8 Live and Extended Thinking, native speech to speech models with background tool calling, 97 ...
Agent-net open sources Webagent, a Go harness that builds guarded, multi-channel AI agents from one declarative JSON spec.
I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is ...
Reward AI's OM-1 is a general-purpose robot policy trained only on human demonstrations, running across arms and humanoids ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results