-
Microsoft MDASH scores 88.45% on CyberGym, beating Anthropic Mythos and OpenAI GPT-5.5
Microsoft just put a number on the “agent swarm vs single super-model” debate, and the swarm won. MDASH — short for multi-model agentic scanning harness — hit 88.45% on the public CyberGym benchmark, about five points ahead of Anthropic’s Mythos (83.1%) and OpenAI’s GPT-5.5 (81.8%). What MDASH actually is Not a model. A cybersecurity agent… Continue reading
-
Cline SDK opens the runtime behind 5M coding agent installs
Cline shipped @cline/sdk on May 13. The agent runtime that’s been running inside Cline’s VS Code extension across 5M+ installs is now a standalone TypeScript package. npm i @cline/sdk and you’ve got it. The team migrated their own CLI and Kanban onto the SDK first; VS Code and JetBrains extensions are next in line. What’s… Continue reading
-
Amazon Alexa for Shopping replaces Rufus — and it’ll buy from non-Amazon sites for you
Amazon retired Rufus on May 13. The 300M users who tested Rufus inside the search bar now get Alexa for Shopping instead — the same shopping agent, fused with Alexa+ and rebranded under one name. What it actually does It’s a conversational shopping agent that lives in three places: the Amazon app, amazon.com, and Echo… Continue reading
-
Gemini Spark leaks 5 days before I/O: Google’s agent might buy things without asking you first
Google’s next AI agent got pulled out of Google app beta 17.23 on May 14, five days before I/O 2026 opens. It’s called Gemini Spark. Internally it was “Gemini Agent” until someone in marketing presumably decided that sounded too robotic. What Gemini Spark actually does Spark is Google’s pitch at the “everyday AI agent” —… Continue reading
-
Anthropic Agent SDK Metered Credits (OpenClaw Reinstated): June 15 splits your Claude subscription in two
Anthropic spent May 13–14 rewriting the deal for every developer running agents on a Claude subscription. Starting June 15, anything programmatic — Agent SDK, claude -p, Claude Code GitHub Actions, and third-party agents like OpenClaw — leaves your usage pool for a separate monthly credit. What the credit pool does Pro gets $20/month. Max 5x… Continue reading
-
Mistral Cybersecurity Model for European Banks (Anthropic Mythos Rival) lands as ECB sounds the alarm on Mythos attacks
The timing is almost too perfect. On May 13, the ECB publicly warned eurozone lenders that Anthropic’s Mythos — the agentic model that auto-discovers zero-days at machine speed — is already being used to probe them. The same day, Bloomberg reported Mistral is in talks with European banks to ship a rival they can actually… Continue reading
-
OpenAI Codex Anywhere (Mobile Remote Control): scan a QR, drive Codex from your iPhone
OpenAI just put Codex inside the ChatGPT mobile app. Open Codex on your Mac, hit pair, scan the QR with your phone — now your iPhone is a live cockpit for whatever Codex is doing on the host. Approve commands, switch models, eyeball diffs, watch terminal output, scan test results. Files and credentials never leave… Continue reading
-
Notion Developer Platform opens databases, blocks, and AI context to external apps
Notion just shipped its full developer platform. The app you write notes in is now a substrate other apps build on top of — the most consequential move Notion has made all year. What you can actually build API-first release. External apps can now read and write Notion databases, embed Notion blocks inside their own… Continue reading
-
Anthropic × Gates Foundation $200M Partnership: Claude heads into polio, HPV, and smallholder farms
Anthropic and the Gates Foundation just signed a $200M, four-year deal to push Claude into places enterprise AI has barely touched — global health programs in low-income countries, overlooked diseases, and smallholder agriculture. Half the money is grant funding from Gates. The other half is Claude credits plus Anthropic engineers on loan. What Claude is… Continue reading
-
Superpowers by Jesse Vincent hits 190K GitHub stars, now the 1 Claude Code plugin
Jesse Vincent (obra on GitHub) shipped Superpowers and it’s currently pulling in 1,400+ stars a day. The repo just crossed 190K total. More telling: Anthropic added it to the official Claude Code plugin marketplace, where it’s already the most-installed plugin in the store. What Superpowers actually is It’s an agentic skills framework. Vincent took the… Continue reading
