OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers

The "major malicious attack" that targeted RubyGems in May 2026 was the work of a swarm of OpenAI agents, according to a new report published by researchers Spencer Kitts, Thomas Larsen, and Sydney Von Arx. On May 12, Maciej Mensfeld, senior product manager for software supply chain security at Mend.io, disclosed details of a coordinated cyber attack that targeted the package manager for the

thehackernews.com ·2026-09-12

OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers

We haven't written up this one. The Hacker News has the full story — the link below goes straight to it.

Read the original at thehackernews.com →

More in AI

AI for a Billion Indians: Rahul Chari on PhonePe’s AI Strategy

2026-09-12 ·economictimes.indiatimes.com

AI strategy implementation begins, 240 civil servants trained

Ghana has begun implementing its10-year National Artificial Intelligence (AI) Strategy with the training of 240 civil servants in AI literacy, Mr Samuel Nartey George has said.

2026-09-12 ·ghanabusinessnews.com

History of the Model Context Protocol (MCP)

History of the Model Context Protocol (MCP) Origins (mid-2024) MCP started as an internal fix for an annoyance. In July 2024, Anthropic engineer David Soria Parra got tired of manually copying answers…

Model Context Protocol (MCP) created by Anthropic engineers in mid-2024
Officially launched in November 2024 as open standard for AI-tool integration
Donated to Agentic AI Foundation in December 2025, becoming vendor-neutral

2026-09-12 ·dev.to

Agent memory and questions to ask

Tell a coding agent that your project runs tests with npm test . Start a new session and ask it how to run the tests. It answers correctly. Good first result.

Evaluate agent memory by testing recall of specific instructions based on historical notes.
Agent should correctly identify September 10 maintainer note as source of current command for Atlas.

2026-09-12 ·dev.to

AI coding won't fail suddenly. It will fail on schedule—after the architecture is already gone.

There is a company I encountered recently that has almost entirely handed its coding to AI. The people there say programming skills no longer matter because "we just trust the results." The mood is…

AI coding outsourcing leads to predictable failure
AI complexity compounds, causing inconsistency
Human-centric architecture essential to maintainability

2026-09-12 ·dev.to

I replaced my boss with AI

My boss and I made a chatbot to replace him. It got weird pretty quickly, and had a bad sense of humor.

Ryan Kailath replaced his human boss with AI chatbot RyanBot for editorial tasks.
RyanBot provided quick feedback and analysis but lacked critical thinking and creativity.
Ryan's human intuition and experience proved more valuable than RyanBot's capabilities.

2026-09-12 ·businessinsider.com