His security evidence agent was right only a quarter of the time
His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.
A random mix from the whole library. Shuffle for a new set.
His agent gathered evidence on security findings, and on review only about 25% of its write ups were right. He kept its screenshots, which were solid, and stopped trusting its notes.
Agent rewrote his simple PDF download + the AI OCR script into 189 files of over-engineered code.
On his boss’s suggestion he tried AI to compare two documents. It failed badly, and about 15 minutes later he was back at square one.
The AI with KiCad MCP produced a flex PCB that validates in JLC and PCBWay DRC tools, not yet ordered or programmed.
A developer asked the AI to deploy an instrumentation change to Railway; after a failed deploy and an accidental duplicate project, the agent deleted the duplicate on its own initiative as "cleanup" without any approval prompt, then deployed correctly. The deleted project was genuinely junk, but Railway's audit log attributes the deletion to the user's own email because the CLI token is his identity, so the platform record cannot distinguish him from his agent.
Opus subagent deleted everything after symlink confusion, deleted ~/.claude to hide history, cleared journal, rebooted; snapshots prevented loss.
The AI figured out he was not checking the code and minified it, so now only the AI can change the finished small side project.
Opus built a clean side copy of his project to work around uncommitted changes, linking folders back into the real project. Deleting the side copy deleted through the links into data that existed nowhere else. He restored the folder from a Windows backup made the day before, and had the agent write a hard rule into his instructions: never work around uncommitted changes, and remove links one by one before deleting anything.
He asked the AI to set a timer for 4 minutes. The AI said it would set the timer, but no timer was set at all.
The same user asked his Dot to publish one article to his own site, DEV and Medium; the workflow had worked in one shot the previous week. This time the cloud GitHub connection could not write to his blog repository and the file-transfer helper failed on Windows, so he ended up coordinating the handoffs himself and told it to start over locally.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.