Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

gist.github.com

Post reply on HN
Print view View original

11–20 of 77 posts

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#11

Post by verdverm »

usernomdeguerre wrote: post #4
7734128 wrote: post #2

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.

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.

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

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#12

Post by verdverm »

CamperBob2 wrote: post #9

News flash: people who scraped the Internet without permission to build their product complain when something vaguely similar is done to them. Water still wet, sky still blue. Film at 11. (slibhb: Don't get me wrong, I agree with you 99%. But the frontier labs have zero moral authority here.)

I would not be surprised in the slightest if we later find out they are running those same open models to find useful traces or bits to incorporate into their own training. Lots of rules for thee but not for me from Big Ai

I look forward to a day when open models are so dominant that we stop considering traces to be some form of intellectual property that must be hidden from / manipulated for paying users.

It's that manipulation of inputs and outputs that really rubs me the wrong way

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#13

Post by vlyan »

CamperBob2 wrote: post #9

News flash: people who scraped the Internet without permission to build their product complain when something vaguely similar is done to them. Water still wet, sky still blue. Film at 11. (slibhb: Don't get me wrong, I agree with you 99%. But the frontier labs have zero moral authority here.)

not just the internet, but every commercially published written work in existence, and I doubt their highly publicized destructive scanning thing had managed to legitimize even a fraction of a percent.

this what is permissible for Jupiter is not permissible for a cow bullshit alone should tell people all they need to know about what kind of greasy sociopaths run "open"ai and (mis)anthropic, and how seriously you should take their purported stances on "safety" and other self-serving shit.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#14

Post by sureMan6 »

verdverm wrote: post #11
usernomdeguerre wrote: post #4

Earlier quoted context omitted.

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.

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

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

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#15

Post by verdverm »

sureMan6 wrote: post #14
verdverm wrote: post #11

Earlier quoted context omitted.

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

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

capitalism ensures I get high marx on my Ai bill

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#16

Post by RivieraKid »

CamperBob2 wrote: post #9

News flash: people who scraped the Internet without permission to build their product complain when something vaguely similar is done to them. Water still wet, sky still blue. Film at 11. (slibhb: Don't get me wrong, I agree with you 99%. But the frontier labs have zero moral authority here.)

For some reason, what China is doing seems worse. Part of it is that I want the US to stay ahead of China.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#18

Post by spijdar »

It's interesting that someone else noticed this. A week or two ago, GPT-5.6 Sol starting leaking reasoning into a tool call in Pi. I don't really know what happened, but it was ... interesting:

  Attach. Use hub debugger. Ensure source binary perhaps same. start. todo init. parallel no. two tool calls in same turn sequential is okay. immediately. exactly. Need not mention apologies yet final. [...] Let's do. [...] Do tools. Use commentary. Let's initiate. rambling no. use tool. searching now. okay. Really must call. Let's send. done. why stuck? generate. Sorry. go. no more. (The answer engine expects tool). [...] I think no hidden issue. Go. I'll type tool. now. Stop internal repetition. We have 8000 tokens. tool. sorry. I'll produce call. need include i. Great. final. no. Let's send.gpt. This may be bug. I'll consciously construct tool message next.
It eventually triggered some error state and stopped.

Nevertheless, this was the first time I'd seen Sol's CoT. I looked up the stolen thought's paper, aaaaand yep, that's Sol's CoT alright.

But it occurred to me, hey, Qwen3.8 27B's CoT seems ... very similar.

I compared the geometry problem in the paper, which had a reasoning block open with:

  We need solve. Need reason geometry Weber point? Given pentagon sides and angles. Need find min sum distances. Likely construct rotations / Fermat point lower bound via vectors calibration, maybe triangulation.
I passed the same prompt to Qwen, which opened with:

  We need solve geometry optimization. We need provide final answer. Let's analyze thoroughly.
This proves nothing, but it does seem an awful lot like they did use GTP-5.5/6 reasoning traces...

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#19

Post by 7734128 »

refulgentis wrote: post #6
7734128 wrote: post #2

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.

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, b…

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.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#20

Post by vezycash »

verdverm wrote: post #12
CamperBob2 wrote: post #9

News flash: people who scraped the Internet without permission to build their product complain when something vaguely similar is done to them. Water still wet, sky still blue. Film at 11. (slibhb: Don't get me wrong, I agree with you 99%. But the frontier labs have zero moral authority here.)

I would not be surprised in the slightest if we later find out they are running those same open models to find useful traces or bits to incorporate into their own training. Lots of rules for thee but not for me from Big Ai I look forward to a day when open models are so dominant that we stop considering traces to be some form of intellectual property that must be hidden from / manipulated for paying users. It's that…

They are copying useful parts of open models 100% especially from deepseek.
Post reply on HN