logoalt Hacker News

moffkalastyesterday at 10:04 AM2 repliesview on HN

Obviously it's not going to be of a paid tier 2T sized SOTA model quality, but it can probably roughly match Haiku at the very least. And for tasks that aren't super complex that's already enough.

Personally though, I find Qwen useless for anything but coding tasks because if its insufferable sycophancy. It's like 4o dialed up to 20, every reply starts with "You are absolutely right" with zero self awareness. And for coding, only the best model available is usually sensible to use otherwise it's just wasted time.


Replies

Anduiayesterday at 10:13 AM

That's why I start any prompt to Qwen 3.5 with:

persona: brief rude senior

show 6 replies
ggregoireyesterday at 2:11 PM

> I find Qwen useless for anything but coding tasks because if its insufferable sycophancy

We use Qwen at work since 2.0 for text/image/video analysis (summarization, categorization, NER, etc), I think it's impressive. We ask for JSON and always ask "do not explain your response".