Re:Qwen3.8 is launching and going open-weight soon
by hodgehog11 on Sunday July 19, 2026 @07:11PM
(#48972549)
They are likely assessing based on "raw intelligence" benchmarks, rather than agentic ones. Fable crushes in those, but that doesn't necessarily translate to microscopic rigor, which is what most people use these models for. You only see it when you ask really tough questions.
[ Parent
| on HN ]
There are no comments on this comment yet.