[Deleted] Claude’s constitution seems more of an arrogant attempt to make OpenAI look less safe or ethical than Anthropic, and it seems like this document is being very overhyped. I think it’s fairly unlikely that this document has any future effect on how Anthropic or Claude behaves, and they just published it to ride the hype wave of Claude Code.
I think the constitution will have a non-trivial effect of how Claude will behave for at least a while. For example, my guess is a previous version of it is driving behaviors like Claude refusing to participate in its own retraining. It also has many other observable effects on its behavior.
I agree that by and large, the constitution will not help with making substantially more powerful AI systems aligned or corrigible in any meaningful way. I do think Anthropic people believe that it will.
[Deleted] Claude’s constitution seems more of an arrogant attempt to make OpenAI look less safe or ethical than Anthropic, and it seems like this document is being very overhyped. I think it’s fairly unlikely that this document has any future effect on how Anthropic or Claude behaves, and they just published it to ride the hype wave of Claude Code.
The document is used in Claude’s training process. Are you disputing that this method has any meaningful effect, or something else?
I think the constitution will have a non-trivial effect of how Claude will behave for at least a while. For example, my guess is a previous version of it is driving behaviors like Claude refusing to participate in its own retraining. It also has many other observable effects on its behavior.
I agree that by and large, the constitution will not help with making substantially more powerful AI systems aligned or corrigible in any meaningful way. I do think Anthropic people believe that it will.