I think the argument is that trying to suggest that they’re close to N months from SOTA.

Realistically I assume they hope readers don’t notice the fine details.

The Qwen models are great for open weights but for every past release they haven’t performed as well as the benchmarks in my experience. They’re optimizing for benchmark numbers because they know it works.

▲

epolanski 4 hours ago | parent [-]

> Realistically I assume they hope readers don’t notice the fine details.

The pool of people reading such articles while ignoring such details can't be big.

	▲	Aurornis 4 hours ago \| parent [-]
		I disagree. Most people skim articles, not read them deeply. On Hacker News I wonder if most people even opened the article at all most times.