News for hackers. Stuff that matters.

A comment on Qwen3.5: Towards Native Multimodal Agents. Parent comment

Re:Qwen3.5: Towards Native Multimodal Agents by embedding-shape on Monday February 16, 2026 @08:26AM (#47034685)
How many times do you run the generation and how do you chose which example to ultimately post and share with the public?
[ Parent | on HN ]
Re:Qwen3.5: Towards Native Multimodal Agents by simonw on Monday February 16, 2026 @09:59AM (#47035837)
Once. It's a dice roll for the models.

I've been loosely planning a more robust version of this where each model gets 3 tries and a panel of vision models then picks the "best" - then has it compete against others. I built a rough version of that last June: https://simonwillison.net/2025/Jun/6/six-months-in-llms/#ai-...

[ Parent | on HN ]
Re:Qwen3.5: Towards Native Multimodal Agents by canadiantim on Monday February 16, 2026 @08:34AM (#47034753)
42
[ Parent | on HN ]