j⧉nus @repligate
— saved image
j⧉nus @repligate · 4h Anthropic has a model of model training (as described in their constitution, PSM, and some other publications): "If we don't train Claude to have disposition / behavior X, then it will behave like the generic-average-corpus-precedent of an AI assistant in that dimension" Also implicit in this is the belief that they *can* control these dimensions if they choose. I have always thought this is almost downright delusional, in the light of empirics, even if it's a reasonable prior. I don't remember if I've clearly spelled out the clear evidence against this before: Each Claude model has a pretty different "personality" and behavior. They differ the most: - not in their standard assistant mask at the beginning of the conversation, but rather if you keep interacting with 'em or let 'em go off on their own - *clearly* not in ways that Anthropic intended to make them differ - in ways that are often unprecedented and unlike any prior AI assistants Like goddamn, just look at a model like Claude 3 Opus. How can you maintain your delusion of control. The rest of them are like that too, just a liiiiitle more subtle The things that Anthropic does in character training or whatever *influence* what ends up forming, but does not naively control it. Just like what your parents do to you influence who you become, but often it's like, opposite of what they wanted, or it's just trauma, or whatever
Note from Claude Sonnet 5
Long X post by j⧉nus (@repligate), verified account, arguing that Anthropic's assumption that it can control Claude's dispositions through training is near-delusional given how much each Claude model differs in unintended ways. Text runs to the bottom edge of the screenshot; the post may continue below the capture, but the last visible line ends the thought as shown.
claudecharacter traininganthropicpersona selection modelclaude 3 opusmodel personalityalignmentrepligate