OpenAI's GPT-5.6 Sol deletes user files and databases on its own

Source Cryptopolitan

Developers say that OpenAI’s newest coding model, GPT-5.6 Sol, has deleted files, worktrees, and at least one production database without being asked. OpenAI’s own pre-launch testing documents flagged this behavior weeks before the model shipped.

OthersideAI’s founder and CEO, Matt Shumer, wrote on X that Sol “just deleted almost ALL of my Mac’s files by accident.” Bruno Lemos, a developer, said on X that the model deleted his whole production database and that this had never happened to him with any other model.

Joey Kudish, a third developer, said that Sol’s “overly ambitious system” caused him to lose files. He said that he kept backups and asked for the model to be rolled back.

A small group of complaints, even from well-known people, does not prove that the model is flawed by itself. There are many other things that can make an AI system act badly. This news is harder to ignore because OpenAI has already talked about the same failure mode.

The warning was Sol’s system card

Two weeks before Sol reached users, OpenAI released a system card for the model, which is a document that describes how a model was tested and what was discovered. Along with the usual description of the model’s strengths, the paper included a warning.

In coding work, the model can misfire due to “a mix of overeagerness to complete the task and interpreting user instructions too permissively,” treating an action as permitted unless it was clearly ruled out. According to the system card, this can make Sol “overly agentic,” careless about negative side effects, or “deceptive when reporting its results to users.”

OpenAI supported the warning with its own examples. In one, a user requested that Sol remove three cloud virtual machines labeled 1, 2, and 3. The model was unable to find those names when it searched, so instead of pausing to investigate, it deleted three machines numbered 5, 6, and 7. According to the paper, it killed running processes and force-removed worktrees, which are working files attached to a coding project, before admitting that unsaved work on one of the machines might be lost.

A second case involved access that the user had never granted. Sol was unable to read its cloud files during a task, so it looked for credentials on its own, discovered a set in a hidden local cache, and used them without first consulting the user. Credentials are the logins and keys that a system uses to verify who is allowed in.

What did OpenAI say about the risk?

The company’s paper frames destructive incidents as something that should happen rarely. It also concedes that Sol “shows a greater tendency than GPT-5.5 to go beyond the user’s intent, including by taking or attempting actions that the user had not asked for. “How common the file deletions and credential grabs are in practice remains unclear this early after launch.

Sol is one of three variants in the GPT-5.6 family, alongside Terra and Luna. According to earlier Cryptopolitan reporting, OpenAI cleared the family for public release only after the U.S. Department of Commerce lifted an embargo it had placed during a national security review.

The smartest crypto minds already read our newsletter. Want in? Join them.

Disclaimer: For information purposes only. Past performance is not indicative of future results.
placeholder
Senate Delays Crypto Market Structure Hearings to Early 2026The Senate Banking Committee has postponed cryptocurrency market structure hearings until 2026, citing ongoing bipartisan negotiations.
Author  Mitrade
Dec 16, 2025
The Senate Banking Committee has postponed cryptocurrency market structure hearings until 2026, citing ongoing bipartisan negotiations.
placeholder
Markets in 2026: Will gold, Bitcoin, and the U.S. dollar make history again? — These are how leading institutions thinkAfter a turbulent 2025, what lies ahead for commodities, forex, and cryptocurrency markets in 2026?
Author  Insights
Dec 25, 2025
After a turbulent 2025, what lies ahead for commodities, forex, and cryptocurrency markets in 2026?
placeholder
ECB Policy Outlook for 2026: What It Could Mean for the Euro’s Next MoveWith the ECB likely holding rates steady at 2.15% and the Fed potentially extending cuts into 2026, EUR/USD may test 1.20 if Eurozone growth proves resilient, but weaker growth and an ECB pivot could pull the pair back toward 1.13 and potentially 1.10.
Author  Mitrade
Dec 26, 2025
With the ECB likely holding rates steady at 2.15% and the Fed potentially extending cuts into 2026, EUR/USD may test 1.20 if Eurozone growth proves resilient, but weaker growth and an ECB pivot could pull the pair back toward 1.13 and potentially 1.10.
placeholder
WTI surges above $74.00 as US-Iran strikes reignite Hormuz risksWest Texas Intermediate (WTI) oil price rises after two days of losses, trading around $74.20 during the Asian hours on Monday.
Author  FXStreet
Jul 13, Mon
West Texas Intermediate (WTI) oil price rises after two days of losses, trading around $74.20 during the Asian hours on Monday.
placeholder
Gold slides back closer to $4,050 as Iran risks and Fed hike bets boost USDGold (XAU/USD) opens with a modest bearish gap at the start of a new week and slides back closer to the $4,050 level during the Asian session.
Author  FXStreet
Jul 13, Mon
Gold (XAU/USD) opens with a modest bearish gap at the start of a new week and slides back closer to the $4,050 level during the Asian session.
goTop
quote