Posts

Comments

Comment by lemon10 on Surprising LLM reasoning failures make me think we still need qualitative breakthroughs for AGI · 2025-04-17T20:00:14.665Z · LW · GW

>DeepSeek-R1 is currently the best model at creative writing as judged by Sonnet 3.7 (https://eqbench.com/creative_writing.html). This doesn't necessarily correlate with human preferences, including coherence preferences.

It should be noted that "best at creative writing" is very different from "best at multi-turn writing and roleplaying in collaboration with humans". I haven't used R1 since its first major version (maybe its gotten better?), but it had some massive issues with instruction following, resulting in laser focusing on irrelevant minor details (What's that? The character has anger issues? Better write them breaking or damaging something literally every reply) and generally being extremely hard to guide into actually writing what you want.

So in theory sure, its great at writing stories (and it is, it has a very unique voice compared to other AI) in theory, but using it in multi turn discussions (most practical uses, such as using it to help you write a story) getting it to follow the spirit of the prompt and write in line with what you want it to write feels like pulling teeth.

Comment by lemon10 on Do websites and apps actually generally get worse after updates, or is it just an effect of the fear of change? · 2023-12-13T07:34:17.407Z · LW · GW

The reason steam has avoided rot is because its a private company with a passionate owner who is not bound by the reckless profit seeking inherent in public corporations, and is thus capable of making long term plans even if it will cost the company profits in the short-medium term.

Its frequently the case that companies with strong founders that forge a monopoly manage to keep the company together as they slowly accumulate power and capital until their inevitable passing.

But as you say, everything dies, and once Gabe Newell dies his successor may not be as skilled, or much worse, may simply not care about the vision Gabe had and seek profit above all else.

If the worst comes to pass and Valve becomes a public company I have no doubt that its enshittification will begin in earnest.