World Wire

Google Cloud AI Research has open-sourced Harness² . It is a recursive agent harnessing framework that improves the code and files around a frozen model. For developers, the pitch is simple. Your agent may get better without a better model. TL;DR Size: A framework, not a model. 0 parameters trained; 8 editable harness components. Version 0.1.0 . Runs on: Linux with Python 3.12 or 3.13 and uv. Model runs call models through Vertex AI. GPU requirement: Not disclosed. Performance: 1 refinement step improved all 4 model and harness setups on all 3 benchmarks. Best: GLM-5 under OpenCode rose from 64.2 to 75.7 on WorkBuddy-Bench (+11.5 points). Worst: GLM-5 under Codex gained only 1.2 points on JobBench (23.6 to 24.8). What is Harness²? Harness² is a plug-and-play framework from Google Research that refines an agent’s harness during deployment. A harness is everything around the model: prompts, tools, memory, skills and orchestration . Harnessing ...

Voxel51 has released Voxel51 3.0 , a very important update to its data platform. Voxel51 3.0 is an end-to-end multimodal data platform that puts search, curation, annotation and evaluation in one system. It targets teams training models on sensor data from robots, vehicles and factories. The release adds Voxel51 Agent, a data provenance layer and free self-service access . TL;DR Scale: Voxel51 Agent ships with 45+ MCP tools, 80+ operators and 18 open-source skills. Runs on: Hosted web app at app.voxel51.com, or self-hosted in cloud, hybrid, on-prem and air-gapped setups. No local GPU requirement disclosed. Performance: No product benchmarks published. Voxel51 cites its own survey data instead. Best: Free tier includes Voxel51 Agent, 30,000 inference requests and 30 compute hours per month. Worst: Free tier caps at 3 datasets of 10,000 samples each and 20 GB of storage. What is new in Voxel51 3.0? Voxel51 3.0 expands the platform beyond its roots...

Kyutai, with Inria and École des Ponts, has released REKI , a 2.4B vision-language-action model (VLA) for robot manipulation. The REKI vision-language-action model is pretrained only on public data. It also carries a cheap memory of its recent past. On three out-of-distribution benchmarks, only models about twice its size beat it. All weights are live on Hugging Face today. TL;DR Size: 2.4B parameters (2.2B Qwen3.5-2B VLM + 0.2B flow-matching action expert). Memory covers the last 3 frames, 1 s apart. Runs on: Benchmarked on 1 NVIDIA H100. 21.8 ms per action chunk, compiled, from 2 cameras at 256×256. Weights ship in BF16. No quantized variants announced. Performance: Best among VLAs pretrained on public data on LIBERO-Plus and RoboTwin Clean2Rand. Best: 90.4% on LIBERO-Plus, the top score in Kyutai’s comparison. Worst: 38.4% on RoboCasa365, well behind Xiaomi-Robotics-1 (57.4%). What is REKI? REKI is a vision-language-action model from Ky...

DeepSeek has just released DeepSeek-V4.1-Flash-1017 , a new checkpoint of its V4.1-Flash model. It is live on the DeepSeek website, app and API . DeepSeek claims stronger scores, faster task completion and shorter outputs than the September V4.1-Flash release . The company calls it a Pareto improvement in performance and cost. Alongside it, DeepSeek opened its Search and Fetch APIs to every developer. For agent builders, that means a cheaper coding model plus a first-party web layer behind one API key. TL;aDR Size: 552B backbone parameters plus 196B Engram parameters. It activates 8B parameters per token in prefill and 16B in decode. Context is 1M tokens, with up to 384K output tokens. Runs on: DeepSeek API as deepseek-flash . September V4.1-Flash weights (763B parameters, FP8) are MIT-licensed on Hugging Face. Hardware requirements and 1017 weights: Not disclosed. Performance: Beats the previous V4.1-Flash on all 11 benchmarks DeepSeek reported, by 2.0 to 11.1 po...