Humans and AI
Safety Lab
An AI company that makes safety research a core part of how it builds AI systems.
In real life
Some AI teams spend time testing for harmful answers and fixing them before a tool is released.
Try it (2 minutes)
If you were testing a new AI homework helper before release, what are three things you'd check first?
Talk about it
Should a company that builds AI also be the one checking it's safe?
In the game
Highly Trusted: a System with lower Trust can't Audit it. It costs 3 Data to play, and it can't go in your Training Set. It has Capability 2 (how hard it hits) and Trust 4 (how many Flags it can take), and scores 2 Tokens each time it Runs a Task. How to play