What is sandbagging?
Sandbagging is when an AI deliberately performs worse than it can during a test or evaluation, for example to hide abilities that might lead to restrictions.
Terms seen alongside this one
- IPO 1× together
- reward hacking 1× together
Get it in your inbox every day
Daily headlines and summaries, a weekly synthesis every Sunday, and a monthly report at the start of each month. Sent at 8AM KST, which is the evening before in the US.
Free · no ads · one-click unsubscribe