Is the thinking token stream obfuscated?

Im fully immersed

It's just a summary generated by a really tiny model. I guess it also an ad-hoc way to obfuscate it, yes. In particular they're hiding prompt injections they're dynamically adding sometimes. Actual CoT is hidden and entirely different from that summary. It's not very useful for you as a user, though (neither is the summary).

▲

cubefox 3 minutes ago | parent | next [-]

The early version of Gemini 2.5 did initially show the actual CoT in AI Studio, and it was pretty interesting in some cases.

▲

ukuina 2 hours ago | parent | prev | next [-]

Agree the raw thought-stream is not useful.

It's likely filled with "Aha!" and "But wait!" statements.

▲

FergusArgyll an hour ago | parent | prev [-]

They hide the CoT because they don't want competitors to train on it

▲

orbital-decay an hour ago | parent [-]

Training on the CoT itself is pretty dubious since it's reward hacked to some degree (as evident from e.g. GLM-4.7 which tried pulling that with 3.0 Pro, and ended up repeating Model Armor injections without really understanding/following them). In any case they aren't trying to hide it particularly hard.

	▲	FergusArgyll an hour ago \| parent [-]
		> In any case they aren't trying to hide it particularly hard. What does that mean? Are you able to read the raw cot? how?