Vercel’s Sept 28 changelog puts Anthropic’s Claude Sonnet 5.5 on AI Gateway as anthropic/claude-sonnet-5.5, with Zero Data Retention supported. Wire it via the AI SDK, Chat Completions, Responses, or Anthropic Messages APIs, or run npx vercel ai-gateway setup and pick it in Claude Code or fx.
Shopify added WebMCP checkout (including Shop Pay) for browser agents: get checkout , update checkout , and complete checkout let them read, update, and place orders after buyer auth—no screenshot scraping. It rolls out to eligible merchants alongside Shopify’s hosted MCP server and UCP; Muse and Instinct already partner on agentic commerce…
IMDEA Networks and UC3M found six of nine chatbot web apps (ChatGPT, Gemini, Claude, Grok, Perplexity, Mistral) send conversation titles, prompts, or screenshots to ad/analytics trackers—often with persistent IDs. Cookie rejection barely helps; Grok was worst, exposing public share URLs to seven trackers by default…
The official MCP Python SDK (1.9.1–1.29.1 and 2.0.0–2.1.1) could send client secrets, auth codes, and PKCE keys to an attacker controlled token endpoint when connecting over HTTP OAuth. Fix is 1.30.0 / 2.2.0; ClientCredentials and PrivateKeyJWT users must also set issuer=, clear stored registrations, and rotate secrets if they connected to untrusted servers…
Anthropic’s status page (14:30 UTC Sep 29) is investigating elevated errors: claude.ai and Claude Code in partial outage, with degraded performance on the Claude API and Console. Claude for Government stays operational; no ETA yet…
Perplexity’s Escaping SPACE Part I gave nine models root in the sandbox behind Perplexity Computer: no VM to host escape in 108 runs. With partial network access, four models (Opus 5, GPT 5.6, Kimi K3) reached a blocked URL via DNS spoofing or shared IP OCR; both paths were patched, and 8 of 10 other sandboxes shared the IP issue…
Spotted something we missed? Start a thread.
