Qwen3.6-27B and Qwen3.8-27B are great. They are fast and quite accurate for not having to spend too much time thinking or searching, as other models with comparable scores have to.
But Qwen3.8-Flash-Next, which tops a lot of benchmarks in its category, is the most obvious Claude distill ever, and although I don’t particularly care about how models get trained, I hate the way it sounds and interacts with me.
- Three warts I’d still fix
- Statements are down to the two things code can’t say
- The bug is fixed at the substrate that caused it
- Genuinely good now
- Also worth a conscious nod
- Say the word on 1 and/or 3 and I’ll do them
Not to mention Claude’s over-the-top comments and git commit messages that make you want to scream.
I wish Alibaba would go back to adopting its own style. Qwen3.6-27B and Qwen3.8-27B sound much better.
I usually use skill like openspec when requesting LLM to do something, combining them with matt’s skills like grill-me. I assume both of this skill will make LLM output in certain way as I jump between model, I don’t really notice them. Usually I also ask to ‘talk in basic english language’ or ’ talk in simplified technical english language’ when just asking random things in the codebase. Surely not perfect and better to have normal sounding LLM directly.