Alex Xi's Notes

Tag: pretraining

6 items with this tag.

  • Jul 06, 2026

    tweet-character-ai-pretraining-tricks

    • pretraining
    • character-ai
    • noam-shazeer
    • gradient-compression
    • infrastructure
  • Jul 06, 2026

    tweet-pretraining-kv-cache

    • pretraining
    • kv-cache
    • efficiency
    • training
  • Jul 06, 2026

    tweet-pretraining-vs-posttraining

    • pretraining
    • post-training
    • verifiability
    • research-culture
  • Jul 06, 2026

    synthetic-pretraining-vintagedata

    • synthetic-data
    • pretraining
    • scaling
    • data-quality
  • Jul 06, 2026

    frontier-pretraining-tpu-gpt-oss

    • pretraining
    • tpu
    • jax
    • infrastructure
    • moe
    • open-source
  • Jul 06, 2026

    icl-rm-latent-compression-report

    • reward-modeling
    • latent-compression
    • fewshot
    • pretraining
    • distillation
    • internal-research