Programming · Tabnews · 🇧🇷 Brazil
Following the AI blindly and breaking Linux (and learning from it)
A developer describes how commands suggested by an AI broke their dual boot and what they learned.
- Profession
- Developer, Gamer
- Tools
- LLMs
- Source
- tabnews.com.br ↗
- Country
- 🇧🇷 Brazil
- Report date
- May 20, 2026
- Verified on
- October 24, 2026
What they did
Used AI-suggested commands to tinker with the system and ended up breaking the installation.
How it went
The author's conclusion: don't trust LLMs 100% when changing your system.
Good to know
Back up first and ask the AI to explain each command before you run it.
The prompt
Before giving me commands for [Linux problem], explain what each one does, the risk, and how to undo it. Ask for my distro and version first.
Replace what is in [brackets]. Prompt written by us from the account, not a literal copy of the source. Do not paste other people’s personal data (privacy laws such as LGPD and GDPR apply).
Summary in our own words. Results as stated in the original account; we have not tested or audited them. Read the source ↗ Found a mistake?
Similar cases
01Letting the agent deploy and read production errors on its own
The founder of a deployment platform explains how they designed an MCP server to take the human out of "copy and paste the log".
02Launching a habit app solo and doing the marketing with AI
A dev created Kada, a habit app with no account and no ads, and used AI for marketing.
03Building an "internet TV" in 6 days with a team of agents
A dev created Crom TV, with 24-hour channels of YouTube videos, coordinating several AI agents.
04Asking AI for a specific algorithm for a research project
A developer skeptical of LLMs used Gemini to generate random quantum circuits in the QCOP project.
05Teaching an agent to use your bank's API
A developer created an open source skill so Codex and Claude Code can integrate with the Banco Inter API.
06Set up a 100% local AI coding environment
A junior developer integrated local models into VS Code with Ollama and Cline, with no paid APIs.
07Build a World Cup tracking website with AI help
An engineer built Central da Copa 2026 and explains why it wasn't "just asking the AI to do it."
08Leave a coding agent running for 24 hours and learn from the bill
An experiment letting Claude Code work unsupervised for a full day ended with a high bill and a security scare.