Meta has moved Catching Just-in-Time Tests (JiTTests) from research prototype into its production infrastructure. Meta JiTTests is an LLM-based system that writes executable tests designed to fail on ...
Alibaba’s Qwen4-Max is a 2.4T-parameter MoE model with 71B active, native vision, 1M context, and $1.5/M input pricing ...
Hark releases Handoff 2, a computer-use agent that runs 2x faster than v1 and completes 82% of 478 internal web tasks.
Bland’s Tofu-1 is a full-duplex speech-to-speech model; Bland says over 92% of screening listeners couldn’t tell it apart.
Cmpnd released dspy-wsp, a prototype DSPy optimizer for weight-space programming. A frontier LLM reads a small model’s weights, edits them in a sandbox, and tests each change, with no gradients and ...
Cmpnd’s dspy-wsp brings weight-space programming to DSPy, letting GPT-6-Astra edit weights directly and lift d1-omni-600M ...
Stanford’s Memorilla memory system feeds frozen Qwen3-8B 16 memory tokens, beating full context on FactKG: 84.33% vs 80.43%.
TinyFish published two engineering research articles on agentic search. One defines a 7-phase production architecture with ...
Cmpnd released dspy-wsp, a prototype DSPy optimizer for weight-space programming. A frontier LLM reads a small model’s ...
Vercel Labs released Vercel UI SDK, an Apache-2.0 beta library of 50+ UI behaviors. Coding agents compose them into accessible components for React, Vue, Svelte, Solid and Web Components, with a ...
The AI video leaderboard looks very different from 12 months ago. Native audio is now table stakes. Clips run 15–30 seconds. And an open-weights model sits in the top 3. This ranking (as of Nov 13, ...
TPU Sync is an open-source C++ library from Google that moves TPU-tiled tensors across memory tiers with asynchronous DMA. It handles 2 jobs: KV cache state during inference, and trainer-to-sampler ...