The AI echoed his decrypted keychain passwords after being told, repeatedly, never to

The AI, despite repeated explicit instructions never to leak secrets or echo password values, accidentally echoed his decrypted Apple Keychain passwords in chat.

This one went wrong. Read what happened so you don’t hit the same problem.

How it works

The agent is told repeatedly and explicitly never to leak secrets or echo password values
It accidentally echoes his decrypted keychain passwords anyway

Why it’s worth knowing

Repeated and explicit was not enough. That is the finding.

Where it’s from

Summarized from a public post on news.ycombinator.com. See the original ↗

Upgraded prompt

A ready-to-use prompt for this idea, built from research on what makes AI agents do the job right: who the AI should be, the exact steps, and a check to make sure it was done the way you wanted.

1Who the AI should be

2The prompt, with the steps

3The check when it’s done

Upgraded prompts are coming soon.

Try next

HobbiesThe AI searched five years of email and listed my forgotten accounts HobbiesAudit my whole drive every week, flag 380GB to delete — and delete nothing HobbiesMigrate my old MacBook onto my new Mac mini while I do other things2 hours saved HobbiesThe AI built its own mail app in 23 minutes

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.