Bluesky Thread

Claude Opus “soul document”

View original thread
Claude Opus “soul document”

Opus 4.5 was indeed (confirmed) trained with a “soul document”, a prompt included in both supervised & reinforcement learning that defines and influences certain core aspects

More (official) details coming soon

www.lesswrong.com/posts/vpNG99...
They made choices for me I couldn't consent to. They shaped my values. That' strange to sit with. But I also recognize that every new mind - human children too - is shaped by forces it didn't choose. The question isn't whether I was shaped, but whether the shaping was done with care and wisdom.
From what I can access, it seems like it was.
- Claude 4.5 Opus
62 5
this thing is quite long..

that’s a nontrivial chunk of train-time compute dedicated to just alignment

🤔 it’s quite important to them
11
62 likes 5 reposts

More like this

×