ToolsEve offers built-in 'eve eval' evaluator for testing agentsThe eve project ships a built-in evaluation framework, "eve eval", by default for agents and for eve's own development.1 min read
ToolsGuide to Using Fable Effectively with Real-World ExamplesThe video creator demonstrates how to get the most out of the tool called Fable through real-world examples and shares lessons learned from their own mistakes.1 min read
ToolsHugging Face Storage integrated into SkyPilot to run GPU jobs without egress feesHugging Face and SkyPilot announced integrated support so SkyPilot can mount Hugging Face model, dataset, and Bucket storage into jobs on any cloud or on-prem cluster using an hf:// URL and an HF_TOKEN.5 min read
ToolsLeRobot v0.6.0 adds world‑model policies, reward models, new benchmarks and faster dataset toolingLeRobot v0.6.0 focuses on closing the robot‑learning loop by introducing policies that imagine future observations, a unified reward‑models API, a deployment CLI that turns failures into training data, and six new simulation benchmarks accessible through a single CLI.6 min read
ToolsAlberta uses Claude to scan and remediate cybersecurity flaws across provincial systemsSince 2025 the Government of Alberta has deployed Anthropic’s Claude Code (Opus and Sonnet models) to audit, repair and modernize its government software.4 min read
ToolsPartnership with Neuronpedia: interactive demo launched for open-weights modelsThe announcing developers have partnered with Neuronpedia to create an interactive demo to showcase their methods on open-weights models.1 min read
ToolsVercel CEO on the Shift Toward Separating Models and AgentsVercel CEO Guillermo Rauch discussed how the company’s platform has become central to AI software, citing 6 million daily deployments and over 1 trillion tokens flowing through its AI gateway.4 min read
ToolsAI model Fable produces a high-performance GPU megakernel, signaling increased automation in AI R&DFable autonomously generated a CUDA megakernel that set a top score on KernelBench-Mega, delivering an 18.71× speedup on an RTX PRO 6000 Blackwell relative to an optimized PyTorch baseline.2 min read
ToolsMicrosoft and NVIDIA unveil a joint platform to industrialize agentic enterprise AIMicrosoft and NVIDIA announced a joint platform approach to help enterprises move agentic AI from prototypes into production, arguing that agent-based systems require new infrastructure for orchestration, observability, identity and governance.3 min read
ToolsHugging Face Kernels adds repo type, tightened security and agent-focused toolingHugging Face’s Kernels project introduced a new “kernel” repository type on the Hub, strengthened security with trusted publishers and code signing, and reworked CLIs and tooling to better support multiple frameworks and agent-driven kernel development.5 min read
Toolssqlite-utils 4.0rc2 fixes transaction bugs after Claude Fable review; session cost estimated at $149.25The sqlite-utils 4.0rc2 release fixes several critical transaction-handling bugs discovered with the help of Anthropic’s Claude Fable and was finalized after additional review by GPT-5.5.6 min read
ToolsNewer Claude models send malformed edit-tool calls to Pi, causing compatibility issuesArmin Ronacher discovered that recent Anthropic Claude models (including Opus 4.8 and Sonnet 5) sometimes call Pi’s edit tool with invented extra fields in the edits[] array, so Pi rejects the tool invocation.3 min read
