Recent submissions

Comment · 16 hours ago
> could you guys at least use some of it?

Why would you think that companies want to use this information for your good?

I don't think that they care. Orders of magnitude more resources are poured into A/B retention testing than to user's actual quality of life improvement

Comment · 21 hours ago
That’s a good thing in the long run. It was time for us to grow up and pay our debts.
Comment · 19 days ago
Existential risk can be another big reason
Comment · 1 month ago
No, thanks, I have my own
Comment · 1 month ago
Could've been better if GGUF implemented QTIP format. GGUF representation is a major limitation for llama.cpp quantization performance
Comment · 1 month ago
> If you’re just using a code book to reconstruct a f16 model the only savings you can get are in sending it over the wire.

That’s why you need to use efficient gemm kernels like FLUTE for inference. They are ~as good as what you can do with ternary quantization.

Comment · 1 month ago
If you want sub-2 bit llm, get one that’s already trained in higher precision, and compress it with something like YAQA/QTIP with finetuning or PV-tuning + AQLM/HIGGS
Comment · 1 month ago
Ternary quantization does not make any sense. Vector quantization and trellis based methods are better in this region for PTQ.
Comment · 3 months ago
Why int4? There are a lot of superior 4 bit formats like nf4 from bitsandbytes.
Comment · 3 months ago
> So how can I regain my ability to focus?

Getting diagnosed with ADHD and taking meds did the trick for me.

Not sure how relevant this is, since inability to focus was always an issue for me.

Comment · 3 months ago
Comment · 4 months ago
> manufacturing companies making the flimsiest, cheapest, plastic crap to save 1/3 of a cent on every mop they produce. Designed to work for the least amount of time before needing replaced

We live in a world with such companies, and we can still buy quality things. If there is a demand for the purely-human generated texts, they will be around. Perhaps a lot of people around you will read ai text instead, and you'll get upset because of it, but it's their choice. You'll still have your thing

Comment · 4 months ago
Oh, yes, you are right about watts. My bad
Comment · 4 months ago
> volt-amperes are technically the same unit as watts

volt-amperes are joules

Comment · 4 months ago
Cool way to think about GWh/year:

  1 GWh/year = (10 ** 9) / 24 / 365.25 / (10 ** 6) MW = 0.11 MW

  70 GWh/year = 8 MW
  1755 GWh/year = 200 MW
  252 GWh/year = 29 MW

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton