Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Failing to reason with LLMs (ARC AGI kaggle up...

Failing to reason with LLMs (ARC AGI kaggle update with Llama3)

Lightning talk at PyDataLondon 2024 August, I spoke on the Kaggle ARC AGI competition and how I've pushed on with using Program as Thought and ideas behind Self Consistency and CRITIC to enhance the model-writing capability.
https://www.meetup.com/pydata-london-meetup/events/302434648/

ianozsvald

August 06, 2024
Tweet

More Decks by ianozsvald

Other Decks in Technology

Transcript

  1. Abstractly reasoning – failing with an LLM (next steps for

    ARC AGI) PyDataLondon 2024-08 lightning talk @IanOzsvald – ianozsvald.com
  2. Can LLMs reason? ARC AGI Abstract JSON “initial → target”

    Tried “don’t code, just reason” Llama3 70B pretty smart Llama3 8B writes code pretty well, sometimes Abstraction & Reasoning Challenge By [ian]@ianozsvald[.com] Ian Ozsvald
  3. 30% solutions pretty good! By [ian]@ianozsvald[.com] Ian Ozsvald It counts!

    Comments! Reasonable numpy! Correct substitution!
  4. Big issue – it gets stuck on the same ideas

    Get LLM to read lots of failed model outputs, summarise, then maybe I could ask it to make new strategies? Notes → NotANumber.email newsletter Next steps By [ian]@ianozsvald[.com] Ian Ozsvald