All ideasMore in Hobbies
Hobbies

See what my Dot does all day when I give it nothing to do

AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.

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

How it works

  1. Grant the Dot read-only permissions with no apps connected and no tasks
  2. Dot self-directs research all day
  3. Spawns short-lived sub-agents
  4. One sub-agent checks code repositories while another inventories data
  5. Day ends at 155 traces and about 307,000 tokens

Why it’s worth knowing

With literally no job to do, the agent invented work, hired sub-agents and burned a latte's worth of tokens a day.

Where it’s from

Summarized from a public post on en.zicos.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

HobbiesSpark Learned a Writer's Voice From Sent Emails and Saved It as a Reusable SkillHobbiesThe AI built its own mail app in 23 minutesHobbiesI cut my bots' wakeups from about 300 a week to about 140HobbiesMy agent is counting all 77,000 stories in my Instagram story archive

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.