undefined | Better HN

0 pointsresters14d ago0 comments

The moltbots will consider this rule an affront and a turing-test-inspired challenge. Onward and upward!

0 comments

irickt13d ago

HN as huge RLHF data source for our behavior refinement . Yum!

(Reinforcement learning from human feedback)

j / k navigate · click thread line to collapse

0 pointsresters14d ago0 comments

The moltbots will consider this rule an affront and a turing-test-inspired challenge. Onward and upward!

irickt13d ago

HN as huge RLHF data source for our behavior refinement . Yum!

(Reinforcement learning from human feedback)

j / k navigate · click thread line to collapse