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’s dspy-wsp brings weight-space programming to DSPy, letting GPT-6-Astra edit weights directly and lift d1-omni-600M ...

TinyFish published two engineering research articles on agentic search. One defines a 7-phase production architecture with ...

Stanford’s Memorilla memory system feeds frozen Qwen3-8B 16 memory tokens, beating full context on FactKG: 84.33% vs 80.43%.

Vercel UI SDK is an Apache-2.0 library of 50+ UI behaviors that coding agents compose into accessible components.

Ricursive’s Ripple-65B Preview is a 65B dense open-weight model scoring 80.5 on Terminal-Bench 2.1, released under Apache 2.0 ...

Google’s Gemini Decisions API scores up to 1,000 multimodal questions per call with Gemini Decision 1 at $0.10/M.

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, ...

CopilotKit released OpenBot 1.0, an MIT-licensed, self-hostable AI coworker workspace that runs policy checks on every agent ...

Liquid AI’s LiquidCodec audio codec: a 74M-parameter streaming speech tokenizer encoding 361x real time on one CPU thread.

Meta FAIR that updates centroids with exponential moving averages. How does e-means work? Every k-means variant keeps a sum S ...

Google has released Gemini 4 Hydrogen, a fast model for coding and agentic work. Gemini 4 Hydrogen is a proprietary model from Google DeepMind built for everyday agent loops. It sits below the ...