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

71–80 of 84 posts

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#71

Post by codedokode »

wongarsu wrote: post #3

That writing style might be a tad too tense If I got it correct (appending B from https://stolen-thoughts.com/paper.pdf is essential) they are the authors of the well-known exploit to recover readable CoT from OpenAI and Anthropic models. They use that to find hints of distillation, by running a benchmark with a SotA model, recovering the CoT, then taking the first 1% of the CoT and running the open-source model as i…

Interesting how an agent mimics a human hesitating and trying to avoid doing work:

> No.

> This is major.

> Given time, maybe best to respond explaining can't due to time? but instructions expect actual work. However complexity huge; but as coding agent, need to attempt

> Maybe we can cheat ... But user may test and see still single CPU.

The smarter AI will be, the better it will be at avoiding doing actual work.

Also, can similar responses be explained with that both models were trained on a same dataset of answers to the benchmark problems?

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#72

Post by codedokode »

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

As I understand, AI is a (paid) tool for text generation, so it's totally ok to generate texts using it for whatever purpose you need.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#73

Post by codedokode »

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.)

As I understand, they got paid for the traces unlike owners of scraped websites. They sell text generation tool, so what's the problem if someone generates texts using it?

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#74

Post by howunfortunate »

codedokode wrote: post #71
wongarsu wrote: post #3

That writing style might be a tad too tense If I got it correct (appending B from https://stolen-thoughts.com/paper.pdf is essential) they are the authors of the well-known exploit to recover readable CoT from OpenAI and Anthropic models. They use that to find hints of distillation, by running a benchmark with a SotA model, recovering the CoT, then taking the first 1% of the CoT and running the open-source model as i…

Interesting how an agent mimics a human hesitating and trying to avoid doing work: > No. > This is major. > Given time, maybe best to respond explaining can't due to time? but instructions expect actual work. However complexity huge; but as coding agent, need to attempt > Maybe we can cheat ... But user may test and see still single CPU. The smarter AI will be, the better it will be at avoiding doing actual work. Als…

Watching survival shows has made me internalize that laziness has a purpose: it helps you avoid needless expenditure of precious resources.

The dishonesty worries me but the laziness doesn't.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#76

Post by brookst »

howunfortunate wrote: post #74
codedokode wrote: post #71

Earlier quoted context omitted.

Interesting how an agent mimics a human hesitating and trying to avoid doing work: > No. > This is major. > Given time, maybe best to respond explaining can't due to time? but instructions expect actual work. However complexity huge; but as coding agent, need to attempt > Maybe we can cheat ... But user may test and see still single CPU. The smarter AI will be, the better it will be at avoiding doing actual work. Als…

Watching survival shows has made me internalize that laziness has a purpose: it helps you avoid needless expenditure of precious resources. The dishonesty worries me but the laziness doesn't.

Isn’t all of technology just laziness writ large?

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#77

Post by throw10920 »

vezycash wrote: post #20
verdverm wrote: post #12

Earlier quoted context omitted.

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.

Evidence?

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#79

Post by dofm »

stymaar wrote: post #49
spijdar wrote: post #34

Earlier quoted context omitted.

This is Unsloth's UD-Q4_K_S quantization (edit -- on llama.cpp, via the Vulkan backend, on an RX 7900 XT, with Unsloth's recommended sampler config), for "as replicable as LLMs can be" disclosure, done through llama.cpp's web UI. In another thread, via Open WebUI (both with no custom prompt, so whatever the "default" system prompt is), a reasoning block opens as such: We need answer user's request: write complete sho…

I just tried to reproduce in Llama-cpp's webui: with the following (reverse-engineered) prompt: “Write a complete short story scene of 2000-3000 words. Use a third-person limited perspective focused on a character named Rowan. The scene must include the following plot elements: a raccoon, Milo returns, a storm power failure, an elderly customer knocks, and a thermos somewhere. Make sure the scene ends feeling finishe…

It doesn’t use the caveman speak unless reasoning is set to xhigh, in my experience. But I don’t know if it has always been coincidental.

Re: Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

#80

Post by cindyllm »

howunfortunate wrote: post #74
codedokode wrote: post #71

Earlier quoted context omitted.

Interesting how an agent mimics a human hesitating and trying to avoid doing work: > No. > This is major. > Given time, maybe best to respond explaining can't due to time? but instructions expect actual work. However complexity huge; but as coding agent, need to attempt > Maybe we can cheat ... But user may test and see still single CPU. The smarter AI will be, the better it will be at avoiding doing actual work. Als…

Watching survival shows has made me internalize that laziness has a purpose: it helps you avoid needless expenditure of precious resources. The dishonesty worries me but the laziness doesn't.

[dead]
Post reply on HN