Remix.run Logo
sudosysgen a day ago

Many of these techniques haven't been published very long ago - it often takes a good 6-8 months for techniques to percolate. But also, they come at a complexity cost and, seemingly, also at a stability cost.

hnfong a day ago | parent [-]

Also potentially a performance (in terms of output quality) cost. DeepSeek is cheap on a per token basis but lags behind in the benchmarks, perhaps it was a calculated tradeoff.

petu 17 hours ago | parent [-]

To be fair Deepseek V4 now is just a preview, which likely implies training isn't completed.