The problem with this is obviously that the only GPT 5.5 thoughts that we have access to are from stolen thought.

Qwen 3.8 0902 was trained after the release of the paper on August 10, so it should have seen those specific thoughts.

usernomdeguerre 6 hours ago | parent | next [-]

seems like only the companies in question could run this sort analysis long-term; since they have full access to their CoTs not in public datasets.

▲

verdverm 5 hours ago | parent [-]

and we have to "trust them bro" to be fair and accurate, something I am very unlikely to do given their other false / misleading statements to date

▲

sureMan6 5 hours ago | parent [-]

And the only end result would be that the Chinese trained on their data just like OAI and Anthropic trained on our data so who cares

	▲	verdverm 5 hours ago \| parent [-]
		capitalism ensures I get high marx on my Ai bill

▲

refulgentis 5 hours ago | parent | prev [-]

The thoughts trick was known before their paper / August.

I "independently" "invented" it for the first Anthropic reasoning models because the API required you have thoughts for each assistant message. My app lets you switch AIs within a chat, and their API used to require thinking for all messages if thinking was enabled, so I needed to get a valid thinking stub to insert.

Time has flew by for me the last 3 years, but, I'd guess it's been at least 18 months. And IMHO it wasn't very complicated to work through how to do once you were dead set on making it happen. I expect it was well-known to distillers before the paper.

▲

7734128 5 hours ago | parent [-]

Sure, but TFA is trying to use Qwen's reaction to the thoughts as proof that they did indeed extract thoughts to train on.

My point is that any model trained after August 10 will know of those specific thoughts.

▲

refulgentis 4 hours ago | parent [-]

I'm sorry, it's going over my head still - my reading is "all models with any training after August 10 know how GPT 5.5 Pro thinks", but I'm not sure why - my initial guess was that's when GPT 5.5 was released, but that doesn't seem to be the case (it was released April 23rd).

▲

7734128 4 hours ago | parent [-]

They would know the specific thoughts released by the "stolen thought" paper, which became part of the public internet on August 10.

Unfortunately those are the only thought examples you can use to perform this experiment, as no other are availible.

But as the model should have seen those specific examples, it's not a good signal that Qwen was exfiltrating thinking traces.

▲

irthomasthomas 3 hours ago | parent [-]

Has the method for extracting the COT been blocked, now? Otherwise why could we not generate some fresh samples?

	▲	7734128 3 hours ago \| parent [-]
		I'm not sure how viable it still is. Perhaps it's still possible, and perhas that's exacly what they did in wtich case my objection falls, but I don't know.