[torginus]

My personal take is that there has been no progress - potentially there has been a regression on all LLM things outside of coding a scientific pursuits - I used to have great fun with LLMs with creative writing stuff, but I feel like current models are stiff and not very good prose writers.

This is also true for stuff like writing clear but concise docs, they're overly verbose while often not getting the point across.

[tizzzzz]

I completely agree with your assessment—outside of programming and scientific research, recent LLM progress has been disappointing, and in some cases even regressive. The creative writing capabilities, once a highlight, now feel increasingly bland and generic, with long-form and nuanced storytelling suffering the most.

Ironically, as these models become more “safe” and commercialized, they often lose the spark that made them valuable for creative exploration in the first place. The focus on enterprise and mass adoption seems to be driving them toward mediocrity, at the expense of individuality and depth.

[mynti]

I feel like this comes from the rigorous Reinforcement Learning these models go through now. The token distribution is becoming so narrow, so the models give better answers more often that is stuffles their creativity and ability to break out of the harness. To me, every creative prompt I give them turns into kind of the same mush as output. It is rarely interesting

[leoedin]

Yeah, I’ve had great success at coding recently, but every time I try to get an LLM to write me a spec it generates endless superlatives and a lot of flowery language.