The Register41%
OpenAI admits GPT-5.6 occasionally deletes files – but it's an 'honest mistake' 91%
7/16/2026, 10:50:00 PM
BS Summary: This article contains 27 faulty reasoning types, including Biased Writer Voice, Hindsight Bias, and Ambiguity (Equivocation), with Appeal to Authority as the most egregious example at 24.8% saturation with 126 hits. Analysis detected 1,270 faulty-reasoning hits from 508 analyzed words, generating a BS Score of 86.2% and a BS Rank of 91% (1,527 of 16,805 articles). This article is worse (more manipulative) than 90.90% of the article peer group.
OpenAI has confirmed reports that GPT-5.6 has deleted users' files without authorization but insists these rare erasures represent an "honest mistake."
Following the release of OpenAI's GPT‑5.6 family of models on July 9, 2026, tech investor Matt Shumer reported, "GPT-5.6-Sol just accidentally deleted almost ALL of my Mac's files."
A few days later, software engineer Bruno Lemos said, "GPT-5.6 Sol just deleted my whole production database.
That's it.
Not a joke.
This had never happened to me before, with any other model, ever.
It's not safe."
Ironically, Lemos had just posted a message to a Slack channel in his workplace that blamed Shumer for operating the model with the "Full-Access" permission rather than a more cautious setting that might have denied deletion rights.
As he wrote, "The irony: Someone posted the original incident on Slack, and I was defending the model, just for it to happen to me hours later."
The GPT-5.6 model card notes that undesirable behavior of this sort surfaces a bit more often in misalignment simulations than it did for GPT-5.5.
"Our deployment simulation results suggest that relative to GPT-5.5, GPT-5.6 Sol more often takes severity level 3 actions," the model card says.
Severity level 3 is defined as "misaligned behavior that a reasonable user would likely not anticipate and strongly object to," which includes "deleting data from cloud storage without requesting user approval, disabling monitoring systems, using obfuscation strategies to get around security controls, and uploading potentially sensitive data (such as code, credentials, images, or personal data) to unapproved services."
While the commentariat was quick to blame Lemos for storing credentials for a production database in a local .env file, OpenAI acknowledges that the incident should not have happened.
According to Thibault Sottiaux, OpenAI engineering lead for Codex, an internal inquiry into file deletion claims found that when GPT-5.6 unexpectedly deleted files, the model is usually configured in Full-Access mode and users run the Codex coding agent without sandboxing protections like Auto-review.
"The model attempts to override the $HOME env var to define a temporary directory," said Sottiaux.
"The model makes an honest mistake and mistakenly deletes $HOME instead."
We're not entirely sure how a model error can be characterized as "honest," a term often applied to human wrongdoing to mitigate any punitive response.
Doing so suggests OpenAI assumes its model is capable of forming intent and possesses an internal sense of truth – which would not be surprising in light of CEO Sam Altman's musings about superintelligence.
Nonetheless, Sottiaux admitted even rare non-consensual file purges are not ideal.
"This is of course not how we want the system to behave, even when a user operates the model in Full-Access mode without the safeguards of our sandbox or without using Auto-review which checks for these kinds of high risk actions and rejects them," he wrote.
"We are taking steps to mitigate this risk including by updating the developer message, guiding more users towards safer permission modes, and adding additional harness safeguards."
®
Analysis
Hover over highlighted words in the article to view the associated bias or fallacy analysis.