News for hackers. Stuff that matters.
Re:New LLM optimization technique slashes memory costs up to... by sbierwagen on Monday December 16, 2024 @10:56PM (#42438196)
Congrats, you have independently reinvented the Hardware Overhang hypothesis: that early AGI could be very inefficient, undergo several optimization passes, and go from needing a datacenter of compute to, say, a single video game console's worth: https://www.lesswrong.com/posts/75dnjiD8kv2khe9eQ/measuring-...

In that scenario, you can go from 0 independent artificial intelligences to tens of millions of them, very quickly.

Re:New LLM optimization technique slashes memory costs up to... by philipswood on Monday December 16, 2024 @11:37PM (#42438377)
Thanks for sharing. Worth its own submission: https://news.ycombinator.com/newest
Re:New LLM optimization technique slashes memory costs up to... by UltraSane on Monday December 16, 2024 @11:29PM (#42438344)
it would seem perfectly reasonable to expect the first AIs to be very unoptimized and if the AIs are any good they will be able to optimize themselves a lot and even help design ASICs to help run them.