Strongly agree! This is my best guess for what the most likely pathway would be for ending up with CoT that couldn’t be used as legible evidence of misalignment without the model ever “intentionally” obfuscating anything. One analogy I think of often here is my own personal quickly written notes, which I suspect would be similarly unintelligable.
Strongly agree! This is my best guess for what the most likely pathway would be for ending up with CoT that couldn’t be used as legible evidence of misalignment without the model ever “intentionally” obfuscating anything. One analogy I think of often here is my own personal quickly written notes, which I suspect would be similarly unintelligable.