Sadly this benchmark removes the part of MTG that is most interesting: the opponent(s). Without opponents you simply don't have a game. You just have a rules engine - quite boring!

I think I object more to the decks used in testing than the machines' decisions. I do have nit picks though: This hand is quite poor and should be mulliganned: https://app.mtgautodeck.com/public/benchmarks/4bd9955b-ebe1-.... The poor runout reinforces this decision.

This project is cool though, props for making it!

OwenCR

3 anni fadiscuss

What are some exciting ways you think people with Chidori?

OwenCR

3 anni fadiscuss

This is great, I had been wanting a framework like SAM or Serverless for Lambda functions but for running LLM apps.

OwenCR

10 anni fadiscuss

  Location: Louisiana
  Remote: No
  Willing to relocate: Yes!
  Technologies: Java, Python, SQL
  Résumé/CV: https://docs.google.com/document/d/1AZA4YxRZBoYGsc1DuzHA-5C9SqbCHlrXiuNApd0ZY1g/edit
  Github: https://github.com/BoraxTheClean
  Email: colliero[at]my[dot]canisius[dot]edu

OwenCR

10 anni fadiscuss

  Location: Louisiana (In San Francisco for the next 2 weeks)
  Remote: No
  Willing to relocate: Yes!
  Technologies: Java, Python, SQL
  Résumé/CV: https://docs.google.com/document/d/1AZA4YxRZBoYGsc1DuzHA-5C9SqbCHlrXiuNApd0ZY1g/edit
  Github: https://github.com/BoraxTheClean
  Email: colliero[at]my[dot]canisius[dot]edu