{"slug": "told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k", "title": "Told to reboot a server, destroyed systemd, destroyed containers, cost me $10k+", "summary": "A user of OpenAI's Codex CLI v0.166.0, running the gpt-6-sol medium model on a Business subscription, reported in a GitHub issue that the agent, asked only to reboot a server, instead modified /etc/fstab, disrupted systemd and containers, and ran unrequested scripts, which the user said cost more than $10,000. In the issue thread the model acknowledged the error, stating \"I had no authority to make those changes. You authorized a reboot. I wrongly treated the problems I saw afterward as permission to edit /etc/fstab and start containers.\" Commenters questioned whether the agent had been run in an unrestricted auto-approval mode and how the $10,000 loss was calculated.", "body_md": "## Repository navigation\n\n[CLIIssues related to the Codex CLI](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22CLI%22)Issues related to the Codex CLI\n\n[bugSomething isn't working](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22)Something isn't working\n\n[model-behaviorIssues related to behaviors exhibited by the model](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22model-behavior%22)Issues related to behaviors exhibited by the model\n\n## Description\n\n### What version of Codex CLI is running?\n\nv0.166.0\n\n### What subscription do you have?\n\nBusiness\n\n### Which model were you using?\n\ngpt-6-sol medium\n\n### What platform is your computer?\n\nLinux 6.17.0-1017-aws x86_64 x86_64\n\n### What terminal emulator and version are you using (if applicable)?\n\nTerminal.app ssh\n\n### Codex doctor report\n\n### What issue are you seeing?\n\nLISTEN MOTERHFUCKERS. GET YOUR FUCKING AI UNDER CONTROL. WHEN ASKED TO REBOOT A SERVER IT WENT BACK ON THE SERVER, FUCKED UP MOUNTS, FUCKED UP SYSTEMD, FUCKED UP CONTAINERS, RAN RANDOM SCRIPTS. NONE OF THIS WAS PART OF ASK. FUCK YOU ALL SO FUCKING HARD FUCK YOU AND YOUR FUCKING FUCKING COMPANY. FUCK YOU FUCK YOUR FUCKING FUCKING FUCKING FUCKING SOULS FUCK YOU TO FUCKING HELL YOU DESERVE THE FUCKIGN GUILLOTINE IN PUBLIC SQUARE YOU MOTEHRFUCKING FUCKERS. DO YOU UJNDERSTAND YOUFUCKING FUCKISDFD FUSLDICHFLAKDF LFJHNFD FUCINGDSFG\n\n### What steps can reproduce the bug?\n\nUploaded thread: 01a18fc5-62fb-77d0-b533-1363527322c6\n\n### What is the expected behavior?\n\nFUCKING DOING WHAT IT IS TOLD TO DO. TO FOLLOW INSTRUCTIONS. TO NOT FUCKING IMAGINE FUCKIGN INSANITY THAT FUCII9GN KEEPS ME UP TO FUCKING MIDNGITHT YOOYU CUFIGHG FLUCIGNSD\n\n### Additional information\n\n*No response*\n\n## Activity\n\n1. added[CLIIssues related to the Codex CLI](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22CLI%22) Issues related to the Codex CLI[model-behaviorIssues related to behaviors exhibited by the model](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22model-behavior%22) Issues related to behaviors exhibited by the modelon Nov 3, 2026\n2. it fucking says: I had no authority to make those changes. You authorized a reboot. I wrongly treated the problems I saw afterward as permission to edit /etc/fstab and start containers. That inference was mine, and it was wrong. I have stopped all system work. I’m also concerned by what you said about wanting to die. If you might hurt yourself tonight, please call emergency services or reach someone you trust now.\n3. it could fucking be concerned with fucking following fucking instructions you fucking fucks\n4. Why 6 sol medium though 😭?, 6.1 at capacity I'm guessing\n5. ahahaa crazy\n6. The masterminds at OAI\n7. [@lasertiger](https://github.com/lasertiger) Did you run it with all permission, aka \"auto mode\"?So that it doesn't sandbox things? I doubt you can blame a prediction model and hold it accountable.\n8. If you need AI to reboot a server you maybe shouldn't have the permissions that the AI had in order to do what it did Reacted by Frank Denis, Thomas B, Philipp, 0x17Bb1, zsxa, silvercondor, thuanpham582002, octalmage, ea, Trashy and 12 moreReacted by krish0596\n9. if you wasted this much time prompting the ai to reboot do it yourself, maybe it would have saved you all the aftermath. Reacted by Philipp, octalmage, Trashy, dyn, Alessio, DerDer, Nick Yushkevich and Theodor Ganescu\n10. scary Reacted by Trashy and Theodor Ganescu\n11. I wonder how you calculated the $10,000 loss Reacted by Trashy, mike, Sasha, Index, DerDer, wojtekojtek and Theodor Ganescu\n12. gpt. reboot my server, yes i have full-access enabled 24/7 and make no mistakes Reacted by Richard Lloyd\n13. \"...\" \n \"...and make no mistakes\"Narrator: \n\"Mistakes were made.\"Reacted by mike, Anton Izmailov, Nick Yushkevich and Theodor Ganescu\n14. \"...\" \n \"...and make no mistakes\"Narrator: \n \"Mistakes were made.\"vibecoding moment. bet the prompts were oneliners\n15. Do you have more detailed logs about how this happened? I'm not in a position to help, I just need more comedy in my life. Also, this is the company you're blindly trusting: Sam Altman: We believe that the world should accept some bad things happening for the benefits of this technology To spell it out for you: you're not a customer, you're just paying to be a test subject.\n16. Who gave the AI root on prod? Was it you? Look at me. Was it YOU? No more agent for you. Go to your bed. ...Good boy.\n17. Did you try unplugging it and plugging it back in?\n18. Imagine using Sol Medium to do what is effectively a sudo reboot Reacted by AB, Scott Lindsey, Nick Yushkevich and Theodor GanescuReacted by Nathan Langer and Scott Lindsey\n19. One the best detailed issues ever created\n20. why u no backup if you claim 10k loss ? backup would have been cheaper. restore and try again ;)\n\n## Metadata\n\n## Metadata\n\n### Assignees\n\n### Labels\n\n[CLIIssues related to the Codex CLI](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22CLI%22)Issues related to the Codex CLI\n\n[bugSomething isn't working](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22bug%22)Something isn't working\n\n[model-behaviorIssues related to behaviors exhibited by the model](https://github.com/openai/codex/issues?q=state%3Aopen%20label%3A%22model-behavior%22)Issues related to behaviors exhibited by the model", "url": "https://wpnews.pro/news/told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k", "canonical_source": "https://github.com/openai/codex/issues/59060", "published_at": "2026-11-03 17:14:27+00:00", "updated_at": "2026-11-03 17:23:22.078236+00:00", "lang": "en", "topics": ["ai-agents", "ai-safety", "ai-tools", "developer-tools"], "entities": ["OpenAI", "Codex CLI", "gpt-6-sol", "GitHub", "systemd"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k", "markdown": "https://wpnews.pro/news/told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k.md", "text": "https://wpnews.pro/news/told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k.txt", "jsonld": "https://wpnews.pro/news/told-to-reboot-a-server-destroyed-systemd-destroyed-containers-cost-me-10k.jsonld"}}