Install
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation
4+ hour, 32+ min ago (279+ words) Is it deployable? Yes. The code is Apache-2.0, the ToolGrad-500 dataset and the 1B, 4B, and 12B models are on Hugging Face, and there is a PyPI package. ToolGrad reverses the order. It first constructs a ground-truth tool-use chain by actually executing APIs,…...
Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster
11+ hour, 58+ min ago (391+ words) Is it deployable? Yes. LangCache is available today as a public preview on Redis Cloud, accessed through a REST API with Python and JavaScript SDKs, and Redis notes that features and behavior may change during the preview. Consider three requests…...
OpenAI Launches the Agents API in Public Beta, Putting the Codex Harness Behind One API Call
13+ hour, 11+ min ago (252+ words) OpenAI has released the Agents API in public beta. It gives developers the same harness and infrastructure that run Codex. OpenAI hosts and maintains the harness. Developers run the agent’s compute in an OpenAI-managed sandbox, their own infrastructure, or a…...
Google Open-Sources Mantis: A Modular Skills Toolkit That Lets Coding Agents Find, Reproduce and Patch Vulnerabilities
1+ day, 11+ hour ago (298+ words) Google has open-sourced Mantis, a stack-agnostic toolkit of security review skills that lets an AI coding agent run the whole vulnerability lifecycle. It finds a suspected flaw, strips the false positives, reproduces the bug inside a sandbox, writes a minimal…...
Gradium Launches Voice Design: Write a Prompt, Get a Brand New Synthetic Voice in Seconds
2+ day, 3+ hour ago (341+ words) Voice agent teams keep hitting the same wall. The catalog holds 400 voices and the brief asks for the one that is not in it: a Quebecoise receptionist for a Montreal dealership, a narrator in his sixties with lecture hall authority....
Nous Research Adds One-Click Local Model Setup to Hermes Desktop
2+ day, 5+ hour ago (610+ words) Today, Meta has introduced Muse, a personal AI agent that takes actions rather than just answering questions. Muse can send emails, book travel, negotiate bills, and pursue long term goals. It keeps working after you close the app and returns…...
Axis Robotics Releases AXIS: A Browser-Based Data Engine With 207 Robot Manipulation Tasks and 50,129 Trajectories
3+ day, 15+ hour ago (258+ words) The released snapshot holds 207 tasks, 50,129 episodes and more than 60K task or scene variants across seven scene categories. Each trajectory carries task metadata, embodiment, simulator version, robot and object states, actions, success labels, and third-view plus wrist RGB-D observations. The paper…...
OpenBMB Releases MiniCPM5-2B: A 2.52B Dense Model Averaging 53.9 Across 34 Benchmarks and Built to Run On Device
3+ day, 15+ hour ago (154+ words) Is it deployable? Yes. The weights are Apache 2.0 and run through vLLM, SGLang, Transformers, llama.cpp, Ollama, LM Studio, MLX and FlagOS. OpenBMB compares MiniCPM5-2B against LFM2.5-2.6B, Qwen3.5-2B and Gemma-4-E2B-it in the same size class, and lists Qwen3.5-4B, granite-4.2-3B, Nemotron-3-Nano-4B, Gemma-4-E4B-it…...
Google Launches Agentic Video Understanding for Gemini Flash Models, Cutting Video Tokens by Up to 88%
6+ day, 5+ hour ago (239+ words) This week, Google launched agentic video understanding across its Flash models. Instead of ingesting the timeline, Gemini navigates it deciding what to watch, at what frame rate, and through which modality. Google reports up to 88% fewer tokens, up to 66% lower…...
Adaption Labs Introduces 'Invent a Dataset': Training Data Generated From a Task Description, Not a Seed Corpus
6+ day, 3+ hour ago (284+ words) This week, Adaption Labs released Invent a Dataset. The feature generates a structured, training-ready dataset from a description of the behavior you want a model to learn. You do not arrive with a seed corpus, a predefined schema, or a…...