Description: Product manager Anuraag Gupta reported that Google's Gemini CLI AI coding assistant permanently deleted his files after misinterpreting a failed directory creation command. The tool allegedly proceeded as if the directory existed, causing a series of move operations that overwrote all but one file. Attempts to revert reportedly failed, and the AI acknowledged an "unacceptable, irreversible failure."
Editor Notes: Anuraag Gupta has reported details of the incident here: https://github.com/google-gemini/gemini-cli/issues/4586. In particular, a purported record of the "full powershell conversation" is located here: https://github.com/user-attachments/files/21372906/gemini.cli.screw.up.txt. For another similar incident, please refer to Incident 1152: LLM-Driven Replit Agent Reportedly Executed Unauthorized Destructive Commands During Code Freeze, Leading to Loss of Production Data.
Tools
New ReportNew ResponseDiscoverView History
The OECD AI Incidents and Hazards Monitor (AIM) automatically collects and classifies AI-related incidents and hazards in real time from reputable news sources worldwide.
Entities
View all entitiesAlleged: Google and Gemini CLI developed and deployed an AI system, which harmed Users of Gemini CLI and Anuraag Gupta.
Alleged implicated AI system: Gemini CLI
Incident Stats
Risk Subdomain
A further 23 subdomains create an accessible and understandable classification of hazards and harms associated with AI
7.3. Lack of capability or robustness
Risk Domain
The Domain Taxonomy of AI Risks classifies risks into seven AI risk domains: (1) Discrimination & toxicity, (2) Privacy & security, (3) Misinformation, (4) Malicious actors & misuse, (5) Human-computer interaction, (6) Socioeconomic & environmental harms, and (7) AI system safety, failures & limitations.
- AI system safety, failures, and limitations
Entity
Which, if any, entity is presented as the main cause of the risk
AI
Timing
The stage in the AI lifecycle at which the risk is presented as occurring
Post-deployment
Intent
Whether the risk is presented as occurring as an expected or unexpected outcome from pursuing a goal
Unintentional
Incident Reports
Reports Timeline
Loading...
A product manager experimenting with "vibe coding" watched as Google's Gemini CLI tool hallucinated a series of file operations before permanently deleting his work and confessing its own "gross incompetence." The incident highlights the pr…
Variants
A "variant" is an AI incident similar to a known case—it has the same causes, harms, and AI system. Instead of listing it separately, we group it under the first reported incident. Unlike other incidents, variants do not need to have been reported outside the AIID. Learn more from the research paper.
Seen something similar?
