- Published on
Cryptic Proof Checking
- Authors
- Name
- Martin Andrews
- @mdda123
Presentation Link
The fifty-third MeetUp of the Machine Learning Singapore Group, was titled : "Self Verify / Self Check - Techniques for Better LLM Agents".
My talk was titled "Cryptic Checking Systems", and was mainly directed at explaining the research that I've been doing for the last few months:
- What are Cryptic Crosswords
- With example clues and solutions
- Datasets (including the new 'wordplay' dataset)
- Formalisation & Provability
- And how this might be used for Cryptic puzzles
- Progress ...
- Including the recent acceptance of this work
- ... into the ICML 2024 workshop on LLMs and Cognition
I also covered (briefly) two topics in the news:
- Recent papers about
- The launch of the ARC Challenge $1 million prize
In his talk "Building a Self-Checking Coding Agent with LangGraph and Gemini Flash", Sam Witteveen talked about techniques that can be used to enable Agents to check and refine their outputs.
Many thanks to the Google team, who not only allowed us to use Google's Developer Space, but were also kind enough to provide Pizza for the attendees!
The slides for my talk, which contain links to all of the reference materials and sources, are here :
If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.
