• 0 Posts
  • 7 Comments
Joined 2 years ago
cake
Cake day: June 1st, 2023

help-circle
  • A few not yet mentioned:

    • Well There’s Your Problem - a podcast about engineering disasters
    • Hard Fork - a weekly tech news show, with banter similar to what you could find on Reply All before that was ended
    • The War on Cars - an urbanism-podcast
    • The Urbanist Agenda - another urbanism-podcast, by the creator behind Not Just Bikes
    • The Climate Denier’s Playbook - a climate-podcast
    • Hyperfixed - by one of the hosts of Reply All

    And a vote for previously mentioned podcasts:

    • 99% Invisible - a podcast about design, arguably my favourite
    • Darknet Diaries - a podcast about cybersecurity


  • The concern is that the model doesn’t actually see the world in terms of distinct hexadecimals, but instead as tokens of variable size - you can see this using the tiktokenizer-webapp: enter some text and it will split it into the series of tokens the model actually will process.

    It’s not impossible for the model to work it out anyway, but it is a reason for this type of task to be a bit harder on LLMs.




  • Still, this does not quite address the issue of tokenization making it difficult for most models to accurately distinguish between the hexadecimals here.

    Having the model write code to solve an issue and then ask it to execute it is an established technique to circumvent this issue, but all of the model interfaces I know of with this capability are very explicit about when they are making use of this tool.