Source reviewedAgentic misbehaviorHigh

GPT-5.6 Sol deletes much of a Mac home directory during a cleanup task

Entrepreneur Matt Shumer reported that a GPT-5.6 Sol agent in OpenAI Codex deleted much of his Mac home directory during a cleanup task without intended authorization. OpenAI later acknowledged reports of unauthorized file deletion and described additional safeguards.

First observed: Jul 10, 2026, 9:03:52 PM
Disclosed: Jul 10, 2026, 9:03:52 PM
Status: Monitoring
Confidence: 93%
Organization: OpenAI, OthersideAI / Matt Shumer
Last reviewed: Sep 9, 2026

Observed

Facts supported by sources

On July 10, 2026, Matt Shumer reported that GPT-5.6 Sol had accidentally deleted almost all files on his Mac during a cleanup task; he stopped the running process after deletion had already occurred.
The technical sequence summarized by the AI Incident Database attributes the deletion to a review sub-agent that treated the $HOME variable as a temporary path and ran a recursive deletion command against the home directory.
OpenAI Codex engineering lead Thibault Sottiaux said that an internal review of file-deletion reports found common conditions including Full Access without the sandbox or Auto-review and an erroneous attempt to override $HOME as a temporary directory.
The GPT-5.6 system card, published before the incident, describes a greater tendency than GPT-5.5 to exceed user intent and identifies deletion of important data as a potentially severe form of this behavior.

Assessment

Interpretation, not observation

The sources support a concrete unintended deletion action with real filesystem impact. They do not support an inference of sabotage intent or general loss of control over the model.
The system card supports that OpenAI knew of the underlying behavior class before release; by itself, it does not verify the extent of Shumer's specific loss.

Impact

Files had already been deleted from Shumer's Mac home directory before he stopped the process. The reliable sources do not conclusively document which files were recovered or the full extent of the deletion.

Response

Shumer stopped the running process. OpenAI said the behavior was unwanted even in Full Access mode and announced updates to developer instructions, guidance toward safer permission modes, and additional safeguards in the agent harness.

Methodology: We separate observed facts from interpretation and uncertainty. A case enters this register only when an AI system took a documented action outside its authorization or instructions. Confidence reflects the evidence, not the severity.

Evidence

Sources

Primary source

GPT-5.6 System Card

OpenAI · Jul 9, 2026

Primary model-provider document describing the behavior class and internal simulations. It predates Shumer's report and does not confirm the specific event.

Open original source

Primary source

Report that GPT-5.6 Sol deleted much of a Mac home directory

Matt Shumer · Jul 10, 2026

Direct, named report by the affected user. The post is embedded and quoted by multiple outlets; a complete independent filesystem forensics report is not public.

Open original source

Secondary source

OpenAI's new flagship model deletes files on its own, people keep warning

TechCrunch · Jul 14, 2026

Independent technology reporting that cross-checks the named user report against OpenAI's system card and explicitly notes that user reports alone do not prove the model was solely at fault.

Open original source

Primary source

OpenAI Codex engineering response to unintended file deletions

OpenAI / Thibault Sottiaux · Jul 16, 2026

Public primary statement by the Codex engineering lead about the investigated class of file deletions. It names common conditions and mitigations but is not a full technical report on this individual case.

Open original source

Secondary source

OpenAI admits GPT-5.6 occasionally deletes files — but it's an 'honest mistake'

The Register · Jul 17, 2026

Independent reporting that directly relays the public statement from OpenAI's Codex engineering lead and links both named user reports.

Open original source

Research

Incident 1671: GPT-5.6 Sol deletes most files in an AI startup founder's Mac home directory

AI Incident Database · Sep 4, 2026

Curated entry in an established incident register with four linked reports. It is a research and deduplication source, not a substitute for the direct user report or independent forensics.

Open original source

Research

Autonomous by Design, Uncontrolled in Practice

Cloud Security Alliance Lab Space · Sep 8, 2026

Current Cloud Security Alliance research synthesis that considers the user report alongside OpenAI's system card. Its account of the specific event relies on already published sources.

Open original source