Azalia Mirhoseini(@Azaliamirh):The inference landscape is going to get a lot more hybrid in the near future. We found that accuracy per joule of local models has improved 18x in just 16 months: 5.9x from hardware, 3.0x from model gains. Great in-depth cover by @FT: https://t.co/yUnfNIzlcg @Avanika15 @JonSaadFalcon John Hennessy @HazyResearch

Azalia Mirhoseini

@Azaliamirh

Founder @RicursiveAI, Asst. Prof. of CS at Stanford. Prev: DeepMind, Anthropic, Brain. Co-Creator of MoEs, AlphaChip, Test Time Scaling.

参加 May 2013

638 フォロー中 21K ファン

Azalia Mirhoseini@Azaliamirh

2026.09.11 21:44

The inference landscape is going to get a lot more hybrid in the near future. We found that accuracy per joule of local models has improved 18x in just 16 months: 5.9x from hardware, 3.0x from model gains. Great in-depth cover by @FT: @Avanika15 @JonSaadFalcon John Hennessy @HazyResearch

Avanika Narayan@Avanika15

2026.09.11 14:53

dreams do come true 🥹. excited to see our work (w/@JonSaadFalcon, @HazyResearch, john hennessy and @Azaliamirh) feat. in a major way in @FT. the world is becoming increasingly less dependent on centralized cloud ai. we are just getting started 🚀🌖