Qwen 3.8 follows GPT-5.5 Pro reasoning prefills
What happened
Qwen 3.8 is a new large language model that adopts the same “reasoning prefills” trick used in OpenAI’s GPT‑5.5 Pro, where the model is primed with a short chain‑of‑thought prompt before answering. This lets Qwen generate more logical, step‑by‑step responses without extra engineering, narrowing the performance gap with the latest OpenAI models.
Why it matters
By copying GPT‑5.5’s prompting technique, Qwen shows that advanced reasoning can be achieved through prompt design rather than massive model scaling, prompting other developers to adopt similar prefills to boost their own models’ capabilities.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from gist.github.com and summarised automatically by AIPulsee's pipeline. See how it runs.