Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

> For those who haven't realized it yet, Deepseek-R1 is better than claude 3.5 and better than OpenAI o1-pro, better than Gemini.

Worse at writing. Its prose is overwrought. It's yet to learn that "less is more"



That's not what I've seen. See https://eqbench.com/results/creative-writing-v2/deepseek-ai_... , where someone fed it a large number of prompts.

Weirdly, while the first paragraph from the first story was barely GPT-3 grade, 99% of the rest of the output blew me away (and is continuing to do so, as I haven't finished reading it yet.)

I tried feeding a couple of the prompts to gpt-4o, o1-pro and the current Gemini 2.0 model, and the resulting output was nowhere near as well-crafted.


What you linked is actually not good prose.

Good writing is how people speak.

Your example is overstuffed with similes.

Just because you can doesn't mean you should.

> He sauntered toward her

"sauntered" - nobody actually talks like this. Stuff like that on each paragraph.

It's fanficcy


"If you're here to Instagram the ‘quaint Welsh charm,' the taxidermied raven's in the back. Five-pound fee for posers."

Pretty snappy, IMHO. Yes, it descends into Bulwer-Lytton territory in a few places, but for every instance where that happens, there are several others where it comes up with something well above par. I'm super impressed, if the examples in the link are really from this model.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: