Need help?
<- Back

Comments (14)

  • armcat
    There has been extensive research into token-free LLMs, but for some reason we are still operating in a token domain, so there is something to that.Byte Latent Transformers (BLT): https://arxiv.org/abs/2412.09871Charformer: https://arxiv.org/abs/2106.12672
  • mrkn1
    subword tokenizers were never causal in the first place, so BPE was peeking at future bytes all along! TIL
  • anon
    undefined
  • JonChesterfield
    Weird paper. Models have had tokens for each byte for ages now. They can read and write individual bytes just fine, in addition to also having multibyte tokens.
  • serioussecurity
    Wow nature got rolled. Should have stayed closer to their expertise. They were already being hustled by a lot of the applied AI work they were accepting.
  • BitProgram
    [flagged]
  • anon
    undefined
  • singularityisne
    [flagged]