agent harness - Page 5
Stories from agent harness come first, newest first, then stories from connected topics (coding agents, AI Agents, MCP, AI Agents, Open Source, Developer Tools), each labelled with where it comes from. This view is not indexed by search engines.
Latest
Gemini Decisions API Launches With Gemini Decision 1
Google launched the Gemini Decisions API and Gemini Decision 1, at $0.10 per 1M input tokens with no output tokens billed, on 11 November 2026.
AWS Emulator Is a Local Tester Written by Autonomous Agents
Amazon says agents wrote AWS Emulator, a CC0 local AWS API tester with no additional service fee, not for production or security testing.
IBM and Microsoft Launch the Imagine Enterprise Agent Platform
IBM and Microsoft have launched Imagine Enterprise, starting with more than 6,000 pre-built AI agents and assets for industry-specific work.
Google Cloud Adds Meta Muse Ember, Spark 1.3 and Wonder
Meta’s Muse Ember, Spark 1.3 and Wonder are now on Google Cloud as managed APIs, under separate Meta terms, not as a Google product.
IFM Releases PAN 2 Open World Model With Training Code
IFM has released PAN 2, an open world model that turns a scene and a text action into 20-second videos. Its benchmark rankings are IFM’s own.
OpenAI Starts Businesses in ChatGPT and Agents Beta
OpenAI has put Businesses in ChatGPT in beta. Business Agents are limited to eligible US online firms, and claiming does not guarantee visibility.
Claude Sheets and Whiteboards Enter Beta; Data Goes Live
Claude Sheets and Whiteboards are in beta on paid plans, and Claude Data is generally available. Claude Meetings is coming soon and has not launched.
Vanta Agrees to Acquire Pillar Security for AI Governance
Vanta has signed a definitive agreement to acquire Pillar Security. The planned AI Governance product is due in January 2027; no price was disclosed.
AlphaProof Code Formally Verifies Signal’s libsignal Code
DeepMind says AlphaProof Code verified compiled libsignal in a CLI harness with hooked primitives, generating over six million lines of Lean.
NEAR AI Breach Exposed About 100 Users via SGLang Flaw
NEAR AI says an SGLang flaw let an attacker into one inference server, exposing about 100 users' details. NEAR Protocol was not affected. No CVE is named.
Latest on TSN
Explore the TSN Atlas: Every topic we cover, mapped. Click a bubble to dive in.
