skip to the stream
← upsy.si
sources
LessWrong
31m ago
energy 127
Some thoughts on GRAFT and follow-up work
read the original at LessWrong →
This source publishes only a summary in its feed, so the full article lives at the outlet. The link above and below goes to the original.
more from the stream
Making alignment the agent's problem
(LessWrong)
Subtly wrong advice misaligns models more than obviously wrong advice
(LessWrong)
Smaller NLAs and probes read eval awareness as well as full size NLAs
(LessWrong)
← back to upsy.si