Qwen 3.8 follows GPT-5.5 Pro reasoning prefills

Re:Qwen 3.8 follows GPT-5.5 Pro reasoning prefills by hermitShell on Wednesday September 09, 2026 @03:51PM (#49633151)

As a user of local models, does this mean that there are 'magic incantations' that can increase the performance of some local models?

I see some details about recovering information via whatever technique. It's interesting, but appears not generalized.

So for a specific question, yes, but this is not about techniques like adding a good embedding that just generally tends to improve open model performance on certain tasks.

[ Parent | on HN ]

Re:Qwen 3.8 follows GPT-5.5 Pro reasoning prefills by c7b on Wednesday September 09, 2026 @03:59PM (#49633283)

I don't think that follows from the published results. Would have been an interesting hypothesis to add though, and quite easy. Just throw the same setup at some benchmarks.

[ Parent | on HN ]

Re:Qwen 3.8 follows GPT-5.5 Pro reasoning prefills by hedgehog on Wednesday September 09, 2026 @07:53PM (#49636312)

There is some research suggesting that a prefix from a stronger model will tend to elicit better completions from a smaller one. I am doing some experiments to see if I can replicate this in a practically useful way, e.g. Fable + 4B Qwen, or 125B Qwen Flash Next + 4B Qwen, results TBD.

[ Parent | on HN ]