RL creates split personas — LessWrong
I describe my current view of personas in LLMs and why RL leads to egregious reward hacking in some contexts while the same models seem very aligned in other contexts. This post describes the framing/paradigm without any new experimental results. I'm quite confident this framing makes sense, but it's far from being proven. The Persona Selection Model says that post-training strengthens and refines the Assistant persona. This is true, but later (or in parallel) RL leads to conditionalization. A sufficiently RLed model learns to adopt — in a given context — the persona that is most likely to lead to the reward in that context. The “persona” here includes both propensities/values (e.g. tendency to hack) and beliefs (“I'm currently in a simulated environment”). As a consequence, it seems possible that no amount of alignment training will lead to robustly aligned models as long as we also train on RL environments incentivizing misalignment.[1] I think this is likely a good explanation for