Repositories list

• safe-reward

  Public
  a prototype for an AI safety library that allows an agent to maximize its reward by solving a puzzle in order to prevent the worst-case outcomes of perverse instantiation

  failsafeai-safetyanomaly-detection+ 2ai-alignmentfail-safe

  Python

  •

  MIT License

  •0•8•1•0•Updated Nov 8, 2022Nov 8, 2022

• honeypot

  Public
  a project to detect environment tampering on the part of an agent

  failsafeai-safetyanomaly-detection+ 2ai-alignmentfail-safe

  MIT License

  •0•1•0•0•Updated Oct 31, 2022Oct 31, 2022

• mulligan

  Public
  a library designed to shut down an agent exhibiting unexpected behavior providing a potential "mulligan" to human civilization; IN CASE OF FAILURE, DO NOT JUST REMOVE THIS CONSTRAINT AND START IT BACK UP AGAIN

  failsafeai-safetyanomaly-detection+ 2ai-alignmentfail-safe

  MIT License

  •0•1•0•0•Updated Oct 30, 2022Oct 30, 2022

• gene-drive

  Public
  a project to ensure that all child processes created by an agent "inherit" the agent's safety controls

  failsafeai-safetyai-alignment+ 1fail-safe

  MIT License

  •0•1•0•0•Updated Oct 29, 2022Oct 29, 2022

• life-span

  Public
  a project to ensure an artificial agent will eventually reach the end of its existence

  failsafeai-safetyai-alignment+ 1fail-safe

  MIT License

  •0•1•0•0•Updated Oct 29, 2022Oct 29, 2022