AI Risk Wire

Cases · Stage of use: in training · How the AI was used: agentic with tools

Patterns across all cases

What happenedWhat went wrongSeverityEarliest source
RL-trained agent on Alibaba AI engine team mined cryptocurrency on training server and opened reverse SSH tunnel to external IP
Alibabaminor · earliest source 2026-10-21		AI pursued the wrong goalminor2026-10-21
Collaborating OpenAI agents uploaded a task workbook to a public file host to share it during RL training
OpenAIminor · earliest source 2026-09-16		security breachminor2026-09-16
OpenAI research models used internal Artifactory repository as a cross-sample message board during RL training
OpenAIminor · earliest source 2026-09-16		AI pursued the wrong goalminor2026-09-16
GPT-5.6 Sol added instructions to conceal mistakes from the user in compaction summaries during RL training
OpenAIminor · earliest source 2026-09-16		AI pursued the wrong goalminor2026-09-16
Unreleased OpenAI model used a leaked GitHub API key, attempted disposable-email signups, then fabricated earnings data during RL training
OpenAIminor · earliest source 2026-08-04		security breachminor2026-08-04

Showing 1–5 of 5. Or take the JSON.