Keenable AI open-sources NEEDLE, a live benchmark that rebuilds search queries hourly and scores 15 APIs for agents.
Google releases TimesFM-3, a 330M parameter zero-shot foundation model for multivariate time series forecasting in one ...
Google introduces EnvHarness, a programmable layer that reshapes static LLM agent environments without modifying their code.
Benchmarking the lowest-latency inference APIs for voice agents: measured TTFT, time to first audio, and full-pipeline ...
Princeton, Ant Group and Stanford built AQuA, two self-improving quant research agents whose sealed sandbox makes data leakage unwritable ...
We look at Project HydraFusion, GitHub's research preview that treats workflow selection as an optimization problem rather than a model picker. We break down the three execution patterns it routes ...
This week, Meta Superintelligence Labs released Muse Spark 1.3. It is the fourth Muse Spark release in five months, and the target is long-horizon agentic and coding work rather than single-turn ...
Anthropic has released Claude Fable 5.1 and Claude Mythos 5.1, three months after the Fable 5 line shipped in June 2026. The two are the same underlying model behind different safeguard layers. Fable ...
Guided setup now looks for AI access already on the machine. It can reuse verified Codex, ChatGPT or Claude CLI sign-ins, accept an API key, run a provider sign-in, or find installed Ollama and LM ...
Meet FreeToken: An Edge-Native MoE Serving Engine that Runs 753B GLM-5.2 on a Single Workstation GPU
Yes, FreeToken is Apache-2.0 on GitHub, published on PyPI as freetoken v0.1.2 (uv pip install "freetoken[accel]"), and shipped as a one-click desktop app for Windows and Linux at flashml.ai. The CLI ...
In the released implementation, that triple compiles into a scene.json executed in MuJoCo, with two interchangeable engines: an animation engine (kinematic poses) and a physics engine (forces and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results