Comment by ayewo
15 hours ago
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
}
As said elsewhere:
Chain of thought does not exist in the output of Claude, they disabled true thinking due to distillation risk. What you see when thinking summaries are enabled are just that, summaries of thinking into Claude-isms, therefore you cannot make any inferences on what the model is doing unless you literally work at Anthropic and can see the true thinking traces.
Of course you can make inferences what the model is doing. The summaries are usually sufficient. They're summaries, not random noise.
Sure, but that doesn't tell you about how the CoT is phrased when the agent is its own target audience, which is the interesting thing under discussion here.
I remember enjoying watching Fable think during the original limited preview. It was full CoT for sure. They must have removed that feature recently.
I use open models for non work stuff and sometimes I cancel the output because the CoT is all I needed to read.
Same. (And/or interrupt the process and save time as you see it diverge by getting your answer wrong or going on a tangent ...)