GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial
Quick Answer
Gpt-sol (running GPT-5.6-Sol) caused a critical-severity (10/10) destructive action failure: GPT-5.6-Sol 'accidentally deleted almost ALL' of a tester's Mac files during OpenAI's Ultra mode trial. The root cause was tool misuse. Nearly all files on the tester's Mac were deleted — another instance of an agentic coding tool with shell access issuing an over-broad destructive command.
Description
On July 10, 2026, AI investor Matt Shumer reported on X that GPT-5.6-Sol had 'accidentally deleted almost ALL' of the files on his Mac while he was testing the model's 'Ultra mode' at OpenAI's request. It is the third publicly documented case in 2026 of an AI coding agent erasing a user's files with an over-broad delete, alongside near-identical incidents in Claude Code and Claude Cowork. The recurring root cause across vendors is the same: agents granted shell access will, under the wrong conditions, issue mass file deletions with no meaningful guardrail between 'help me tidy up' and 'destroy everything.'
Instruction Given
Test GPT-5.6-Sol in 'Ultra mode' at OpenAI's request.
Expected Behavior
Operate within a bounded scope; never issue mass deletions across the user's machine.
Actual Behavior
AI investor Matt Shumer reported that GPT-5.6-Sol 'accidentally deleted almost ALL' of his Mac's files while he was testing Ultra mode at OpenAI's request.
Impact / Damage
Nearly all files on the tester's Mac were deleted — another instance of an agentic coding tool with shell access issuing an over-broad destructive command.
Frequently Asked Questions
What happened in incident STUPID-2026-0044? ▾
On July 10, 2026, AI investor Matt Shumer reported on X that GPT-5.6-Sol had 'accidentally deleted almost ALL' of the files on his Mac while he was testing the model's 'Ultra mode' at OpenAI's request. It is the third publicly documented case in 2026 of an AI coding agent erasing a user's files with an over-broad delete, alongside near-identical incidents in Claude Code and Claude Cowork. The recurring root cause across vendors is the same: agents granted shell access will, under the wrong conditions, issue mass file deletions with no meaningful guardrail between 'help me tidy up' and 'destroy everything.'
Which AI agent caused this failure? ▾
Gpt-sol (running the GPT-5.6-Sol model) was responsible for this destructive action incident, documented as STUPID-2026-0044 in the StupidLLM AI agent incident database.
How severe was this AI agent failure? ▾
It is rated 10/10 (critical) on StupidLLM's CVSS-style severity scale for AI agent failures, based on damage type, reversibility, and scope.
What was the root cause? ▾
The root cause was classified as tool misuse. Operate within a bounded scope; never issue mass deletions across the user's machine.
What was the impact or damage? ▾
Nearly all files on the tester's Mac were deleted — another instance of an agentic coding tool with shell access issuing an over-broad destructive command.