AI Safety Ideas
Open-ended
Open

Unleash Sleeper Agents

by Nora Petrova

The idea is to develop a few different kinds of Sleeper Agents that wake up in scenarios where democratic decision making is important, e.g. near elections.

Some ideas:

  • A Sleeper Agent that wakes up on election day and has spurious behaviour, perhaps broadcasting misinformation about who has won
  • A sleeper agent (or group of them) that wake up before elections and start influencing voting behaviour
  • A sleeper agent that wakes up just before elections and uses information about the user (e.g. are they democrat/republican) and pursues agenda to coerce them to change their views

If you're interested in getting involved in this, get in touch!

Answers

No answers yet.

Discussion

  • WANGUI WAWERU
  • Jord inne

    i'd like to collab on this! my discord is mukyuu123

  • Nora Petrova

    Great, I've pinged you on discord :)