It has always seemed to me that they're hacking for dopamine response in moderately interested data labelers.

Spot on wrt CoT. I have thinkingSummaries enabled and I find it eminently readable compared to the prose in Claude's replies.

In fact, whenever Claude disobeys me, I usually first skim the CoT to figure out if my original instruction was ambigous given the context. I usually come away with a better understanding of how to frame my prompt to be less ambiguous or just force myself to be more explicit when prompting.

Regarding diosbedience, usually this is either due to a blanket instruction from me during an earlier turn in the same session, an explicit instruction in its system prompt or it being just eager to bring a task to completion.

  # ~/.claude/settings.json
  {
    "model": "opus",
    "showThinkingSummaries": true,
    "skipDangerousModePermissionPrompt": true,
    "verbose": true,
    "remoteControlAtStartup": true,
    "agentPushNotifEnabled": true
  }

I find that Claude Code writes very long comments, longer than even a human trying to be helpful would write.

I figure that it's basically making notes for itself, when it has to revisit the same code in a fresh session.

I think the specific issue with Opus 5 is that its writing style is just trying to cheat at RL. It makes everything hypey yet self deprecating and constantly brings up "honest caveats" because the scoring rubrics look for those.

It's all about conducting users into using their plans/tokens in accordance to a certain cadence

sometimes by increasing human cognitive load during reviews, sometimes by expanding the number of gated decisions, sometimes by penalizing those using their accounts on other harnesses

Yeah, if anything the problem is that the output uses too many words for too little signal, and incorrectly uses confidence based on insufficient information to the degree it’s clearly bullshitting.

I don't know, I just pulled up the status for an active session and here's what it said:

  One thing I found before dispatching, and filed as Q0579. The halt told you C6
  was all that was left in the unit. That was true of the step's criteria and
  false of the unit's acceptance, which reads "exits 0 AND witnessed red" — two
  conjuncts. The witness half holds; the exits-0 half does not, because hello's
  G7 currently reads DIFFER 554/51340. I re-derived that from the gate map
  rather than trusting the prior step's report. So satisfying C6 does not by
  itself finish this unit, and I've filed that so attempt 1's success can't
  quietly be read as the unit's.