OpenAI Hired the Hackers Who Breached It — Your API Is Next
OpenAI just hired the security firm that broke into it. On November 6, Hacktron — the researchers who chained a community forum RCE ...
Iyi 0.20: The Language That Ships Its MCP Server in the Binary
Iyi 0.20 is a Crystal-compatible language where the compiler binary includes the LSP and MCP ...
Mistral Studio Agents SDK: Tool Calls Run by Default — Set a Policy First
Mistral launched managed agents and an Agents SDK on Nov 5. The default auto-approves every ...
Anthropic FlashProve: Prove Your AI Is What You Paid For
Anthropic FlashProve uses zkSNARK proofs to verify which AI model generated a response. 5,500x faster ...
Ripple-65B: 65B Dense Model Beats 500B+ on Agentic Coding
Ricursive Intelligence releases Ripple-65B Preview — an Apache 2.0 dense model scoring 80.52 on TerminalBench ...
sand3d: AI Agents Can Now Build 3D Objects in Under 200 Tokens
sand3d is a Python library that lets LLMs generate clean 3D objects using 4x fewer tokens than Blender Python. Install it today for ...
Android Studio Rabbit 2: Run 40+ AI Agents in Your IDE
Android Studio Rabbit 2 is stable. Install Claude Agent, Codex, Antigravity, or any of 40+ ...
RTK: Cut AI Coding Agent Token Costs by Up to 90%
RTK is a Rust CLI proxy that compresses AI coding agent command output before it ...
AutoGen Is Dead: Microsoft Drops Security Fixes Now
Microsoft's AI Frontiers lab is gone and AutoGen gets no security fixes. Here's what happened, ...
Google ADK 2.14: A2A, Execution Environments Go Stable
Google ADK 2.14.0 ships 42 stable modules including A2A, Computer Use, and MCP server. Three ...