The free Tauri desktop app (macOS, Windows, Linux) keeps a central library in ~/.skillshub, then syncs skills by symlink or copy to 46 built-in tool adapters plus custom dirs, with Explore installs from curated lists or Git and bulk enable/update across global or project scope.
Across 6,840 synthetic call graph refactoring tasks, six agents in Copilot's harness stayed near perfect by scripting around size with tools like grep , while plain LLMs degraded; on SWE bench Verified traces, the count of read and analyze tool calls predicted failures better than lines edited. A new task that merges two near identical classes finally broke the agents, and code plus data are open at github.com/microsoft/CABRA…
HCLTech will stand up an Anthropic Business Unit and CoE for Claude deployments, while HCLSoftware embeds Claude and Claude Code into products such as BigFix and AppScan, and HCLTech's AI Force platform will use them for IT support and code remediation under policy guardrails and human oversight…
Hold ⌃⌥Space and speak: Apple's on device speech stays local, simple opens and window moves skip AI ( 0.08s), and harder asks go through claude p on your existing Claude Pro/Max plan ( 0.14¢ per ask) while learned shortcuts replay without AI. MIT, needs macOS 26+ and Claude Code; Safe mode sandboxes writes to a scratch folder and prompts before deletes, sends, or buys…
Expand's Iris model reads the rendered page, keeps tables and the JSON hidden in the page that other Markdown APIs drop, and links every line back to a saved snapshot; on Expand's own 1,094 question benchmark, agents answered 74% of questions from its output versus 55% for the next best API. It also offers question targeted passages that cut tokens by over 95%, site crawls, and change tracking, and a coding agent can set it up from expand.ai/start.md…
A single policy proposes harness edits (prompts, tools, context, feedback handling) and reflects on their effect, and those runs then train its weights via SFT plus interleaved GRPO, reaching 82.1% on Polyglot and 48.3% on SWE bench Verified versus 62.6% and 41.0% for the best prior self evolution method. The harness loop alone lifted a GPT 5 mini agent from 24.4% to 48.3%, and the evolved harnesses transferred to other benchmarks without further tuning…
Spotted something we missed? Start a thread.