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

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%.

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

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 ...

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, ...

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

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

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 ...

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 ...

IBM has announced IBM Quantum Nighthawk r3, its next superconducting quantum processor. It is designed to run 10,000 quantum operations accurately across 520 programmable qubits. In 2027, IBM plans to ...