Spooky Sale: 10% off Premium yearly · $118.80 for the first year · until Nov 6Get it

Deep-ML
Learn
Problems1,200+ hands-on ML problemsLearning PathA guided route through the fundamentalsLabsInteractive labs on real techniquesProjectsBuild a GPT, an RL agent, CUDA kernelsCollectionsCurated problem sets and videosMathPen-and-paper math for MLIntuitionInvent the idea behind the formula yourselfPlaylistsYour own problem lists, shareableStudy AssistantAn AI teacher that knows your progress
Interview Prep
Compete
ContestsFresh problem sets, ranked liveLeaderboardWhere you stand, globallyBuddiesSolve with a friend: streaks, a weekly board, chat
Discuss
Deep-Path
Premium
      Intuition
      88 of 88

      Don’t redo the work

      A model writes one word at a time after a prompt. Every word in the text, the prompt’s and each one the model writes, needs a key and a value worked out once it’s in the text: that’s what later words listen to in “Listen and collect”. Write work_to_write(prompt_length, new_words): how many words’ keys and values it has to work out to write new_words words after the prompt, if it never works anything out twice.

      prompt_length
      5
      new_words
      3
      solution.pyLoading Python
      ← One outlier ruins it