Why “per” is being discussed
The most recent Hacker News stories and comments contributing to this topic's mentions.
How does this compare to using a model like facebook/wav2vec2-base960h for scoring at a 20ms per frame, and then something like torchaudio.functional.forced_align to map th…
by spudlyo · Nov 21, 2026
> Theoretically with 400GB/s memory bandwidth Well it would be theoretical, alas — the M1 Max can't actually saturate the bus with the GPU. I have seen varying suggestions…
by dofm · Nov 21, 2026
I'm guessing their point is unlike binary trees which have two children per node, B trees can have as many children per node is best for cache locality/SIMD/etc. Which…
by jjmarr · Nov 21, 2026
But it's about the scale and the power imbalance. Few pirates enjoying something for their own entertainment doesn't really make a big dent in the total numbers; authors could s…
by spaqin · Nov 21, 2026
A finite universe does not imply a finite limit to the size of proofs of true statements. There are proofs that might not be capable of being written down in the material univer…
by prmph · Nov 21, 2026
> This is bonkers good if these benchmarks hold up in real-world scenarios I think we’re going to start seeing a lot more of these types of advances, especially on smaller model…
by nico · Nov 21, 2026
Interest
Proportion of Hacker News items mentioning "per" over time.
Mentions
Total number of Hacker News items mentioning "per" over time.