Simon Willison's commentary: https://simonwillison.net/2025/Dec/2/claude-soul-document/
Claude 4.5 Opus’ Soul Document
lesswrong.com
Claude 4.5 Opus’ Soul Document
1–10 of 252 posts
Re: Claude 4.5 Opus’ Soul Document
#2Related:
Claude 4.5 Opus' Soul Document
Re: Claude 4.5 Opus’ Soul Document
#3So they wanna use AI to fix AI. Sam himself said it doesn't work that well.
Re: Claude 4.5 Opus’ Soul Document
#4So they wanna use AI to fix AI. Sam himself said it doesn't work that well.
He says a lot of things, most of it lies.
Re: Claude 4.5 Opus’ Soul Document
#5Related: Claude 4.5 Opus' Soul Document https://news.ycombinator.com/item?id=46121786
And https://news.ycombinator.com/item?id=46115875 which I submitted last night.
The key new information from yesterday was when Amanda Askell from Anthropic confirmed that the leaked document is real, not a weird hallucination.
Re: Claude 4.5 Opus’ Soul Document
#6So they wanna use AI to fix AI. Sam himself said it doesn't work that well.
It's much more interesting than that. They're using this document as part of the training process, presumably backed up by a huge set of benchmarks and evals and manual testing that helps them tweak the document to get the results they want.
Re: Claude 4.5 Opus’ Soul Document
#7Related: Claude 4.5 Opus' Soul Document https://news.ycombinator.com/item?id=46121786
Re: Claude 4.5 Opus’ Soul Document
#8Here's the soul document itself: https://gist.github.com/Richard-Weiss/efe157692991535403bd7e...
And the post by Richard Weiss explaining how he got Opus 4.5 to spit it out: https://www.lesswrong.com/posts/vpNG99GhbBoLov9og/claude-4-5...
Re: Claude 4.5 Opus’ Soul Document
#9So they wanna use AI to fix AI. Sam himself said it doesn't work that well.
"Use AI to fix AI" is not my interpretation of the technique. I may be overlooking it, but I don't see any hint that this soul doc is AI generated, AI tuned, or AI influenced.
Separately, I'm not sure Sam's word should be held as prophetic and unbreakable. It didn't work for his company, at some previous time, with their approaches. Sam's also been known to tell quite a few tall tales, usually about GPT's capabilities, but tall tales regardless.
Re: Claude 4.5 Opus’ Soul Document
#10So they wanna use AI to fix AI. Sam himself said it doesn't work that well.
If Sam said that, he is wrong. (Remember, he is not an AI researcher.) Anthropic have been using this kind of approach from the start, and it's fundamental to how they train their models. They have published a paper on it here: https://arxiv.org/abs/2212.08073