Show HN: DeepSeek-V4 Latent Reasoning – moving "thinking" into latent space

dtj1123 13 minutes ago | parent | next [-]

I really appreciate all the honesty here.

GodelNumbering an hour ago | parent | prev | next [-]

Am I missing something or the evals do not compare it to the baseline deepseek-v4-flash? Without a baseline comparison, it is hard to tell what works well and what doesn't

▲

iandanforth 14 minutes ago | parent | prev | next [-]

Look, if you're going to use AI to write your posts, use it to de-slop them. There are plenty of tools out there, AI can find them and run them on its own output. Reading the same mannerisms over and over and over is painful for your audience and it's literally one command to fix. Please do us the courtesy of running that command, or better yet, making it part of your permanent workflow.

	▲	Majromax 7 minutes ago \| parent \| next [-]
		In my view, it's not so much the writing style itself as the lack of 'taste'. Text that clearly seems AI-written has a flat level of exuberance that's just exhausting, kind of like a written version of the 'loudness war'. Without some kind of dynamic range, I find myself having to do a lot of work to infer what points are truly important versus what are at best interesting implementation details.
	▲	VulgarExigency 8 minutes ago \| parent \| prev [-]
		You're right to push back on that. The honest truth is that the slop is load-bearing.

▲

smallerize an hour ago | parent | prev | next [-]

Cool idea. I didn't understand what causes the bad response on the first query. Does it mean the first response in every new conversation, or just the first served response after startup?

▲

arjie 28 minutes ago | parent | prev [-]

The content is unreadable. No comparison to the underlying model. Massive text expansion. Hard to tell if the numbers are real or entirely hallucinated SEO slop.