|
|
|
|
|
|
by sometimelurker
31 days ago
|
|
|
maybe they're rewarded for being under their estimated implementation time in their training. they could learn a similar behavior (to safely underestimate) in other contexts and that could've spilled over. you can blame everything on wired quirks in the training (claude overusing the words "true" and "genuine" when their not needed, AIs using em-dashes because the pretrain has a ton of them) |
|
|