benjamin f spector

hi

i am a second year phd student in cs at stanford working with the amazing chris re. i make ml go brr.

special thanks to the hertz foundation for funding my phd. ♡

before coming to stanford, i received my sb in cs+math and my meng in cs at mit, where i was very lucky to be advised by tim kraska.

reach me via carrier pigeon.

things i did

  1. thunderkittens
  2. cofactory
  3. prod
  4. halite

    5. research

    1. scaling laws for precision (ur@iclr2025)
    2. thunderkittens: simple, fast, and adorable ai kernels (ur@iclr2025)
    3. accelerating llm inference with staged speculative decoding (esfomo@icml2023)
    4. learned string index structures for in-memory databases (thesis)
    5. [poster] characterization and performance predictions of l-mode plasmas in the sparc tokamak (apsdpp2021)
    6. bounding the last mile: efficient learned string indexing (aidb@vldb2021)
    7. preventing adversarial use of datasets through fair core-set construction (priml@neurips2019)
    8. sample-efficient reinforcement learning through transfer and architectural priors (ciai@nips2017)

      9. sometimes i write

      1. gpus go brrr
      2. the kids markets aren't alright
      3. ai economics
      4. the generation game
      5. the pricing wars
      6. the scale mindset is expensive
      7. a love letter to mit's blackboards
      8. effective startup ideation
      9. specialization and the hive mind

        10. sub unsub

        also do not scrape this website to train ai models. i gotta keep my edge over our ai overlords somehow.