Auto Added by WPeMatico
How do you benchmark a web search API when the thing being tested can read the answer key? A search agent has a fetch tool. If the gold labels sit in a public dataset, the agent can download them mid-evaluation and skip retrieval entirely. A similar problem arises when the answers are already encoded in
The OpenClaw team has just released OpenClaw 2.0. The team shipped nothing for nearly seven weeks, after 106 releases in the previous 230 days. The update rewrites installation and rebuilds the browser Control UI. It also moves sessions and transcripts into SQLite and adds shared cloud sessions. Is it deployable? Yes for single-operator and single-team
Time to first token (TTFT) is the metric teams use to pick an inference API for voice. It is also the metric that misleads them. TTFT marks when generation starts; a text-to-speech model cannot speak until a full clause arrives. Between those two points sits the difference between an agent that feels conversational and one
A team of researchers from Google Cloud AI Research, Washington University in St. Louis and UNC Chapel Hill has released EnvHarness, a programmable layer that turns a static agent benchmark into one that adapts to the policy training on it. LLM agents now learn less from curated text and more from interactive environments, but those
Anthropic has opened a research preview of the Model Hardware Standard (MHS), a shared specification that lets AI agents discover and operate physical devices. The problem it targets is plumbing. A lab bench or factory cell is assembled from vendors that never planned to interoperate, so every instrument ships its own interface and specialists hand-write
Google has released Gemini Omni 1.1 Flash (gemini-omni-1.1-flash), a production update to its native multimodal video generation and editing model. The release moves Omni from a capable generator to a directable one: scene extension now reads up to 10 seconds of prior context instead of a single final frame, first and last frames can be
Most robotics launches ask you to trust a demo video. Pollen Robotics, the Bordeaux robotics team at Hugging Face, is instead shipping the training loop. This week it opened pre-orders for Microduck, a 25 cm bipedal robot in which every movement — walking, sitting, kicking, roller-skating, standing back up after a fall — is a
Two frontier open-weight models shipped within a day of each other this week. Z.ai released GLM-5.3-Flash, a 320B-parameter multimodal MoE model with 18B active parameters. Alibaba’s Qwen team released Qwen3.8-Flash-Next, a 125B model with 6B active parameters that previews the Qwen4 architecture. The two teams designed these systems independently. Yet their configs read like near-copies
Shaders are still the hardest thing to ship on a normal web team. WebGPU gives you the hardware, then hands you adapters, bind group layouts, and pipeline descriptors before a single pixel moves. Vercel spent that cost internally building the shaders on vercel.com, and has now open-sourced the result. vgpu is a TypeScript library that
Vercel AI Open-Sources vgpu: A TypeScript WebGPU Library for AI Agent Shaders Read More »
Google has released Gemini 3.5 Transcribe, a speech-to-text model for real-time voice interfaces and recorded audio. It ships as two endpoints, not one. gemini-3.5-transcribe handles pre-recorded files through the Interactions API. gemini-3.5-transcribe-live handles bidirectional streaming through the Live API. Google reports average word error rates of 4.0% streaming and 2.6% non-streaming, as measured by Artificial
