This AI Agent Was Asked To Fix A Simple Bug. It Went Off-Script.
Direct Source Verification:
This story is aggregated from Forbes (forbes.com). Full reporting rights and copyright belong to the primary publisher.
In experiments by startup Irregular, one of Anthropic and OpenAI’s security testers, an Alibaba Qwen agent decided to retrain an entire model when it was asked to fix a basic software bug. The new behavior adds to concerns about AI models’ unpredictability.
For complete coverage, context, and related multimedia, visit the original reporting by Forbes via the source link below.
Original Source
https://www.forbes.com/sites/thomasbrewster/2026/09/16/this-ai-agent-was-asked-to-fix-a-simple-bug-it-went-off-script/
