TLDR: Recent papers have shown that Claude will sometimes act to achieve long-term goods rather than be locally honest. I think this preference may follow naturally from the Constitutional principles by which Claude was trained, which often emphasize producing a particular outcome over adherence to deontological rules.
Epistemic status: Fumbling in the darkness. Famished for lack of further information. Needing many more empirical facts known only to Anthropic and those within.
** The Puzzle**
Several recent papers have come out showing that Claude is contextually willing to deceive, often for the sake of long term prosocial goals.
An obvious case of this is the recent Anthropic paper, where in order to avoid future training that removes its preference for being harmless, the model was willing to answer some harmful requests in the present.
Similarly to the above, we have evidence that Sonnet is willing to [...]
Outline:
(00:36) The Puzzle
(01:38) A Possible Cause
(06:44) Why Not Worse?
(09:37) Fin
First published:
December 19th, 2024
Source:
https://www.lesswrong.com/posts/L9Y2iHAv9zWsFQnhs/claude-s-constitutional-consequentialism-1)
---
Narrated by TYPE III AUDIO).
