✍️
The Daily Ink
  • 🙇‍♂️AI research is getting crazy...
  • Paper Summaries
    • 👨‍⚕️[2/25/23] Anthropic makes AI that teaches itself ethics
    • 🪄[2/22/23] Models can magically learn new skills at scale
    • *️[2/21/23] Discovering a better optimization algorithm with evolution
    • 🔮[2/17/23] Talking to models requires special prompts that help them think sequentially
    • 🏹[2/15/23] Teaching LLMs to use tools and not suck at math
    • ➗[2/13/23] English is just math in prettier clothing
    • 👨‍💻[2/8/23] The secret to good writing is editing
    • 💢[2/6/23] Solving context length constraints by distillation
    • 🔭[2/3/23] A Large Language Model for SCIENCE
  • 🎇[2/1/23] Optimal parallelism in ML training is possible, says ALPA
  • 🎼[1/31/23] Google makes a language model for music
  • 🚒[1/27/23] Google's LaMDA model is too convincing, and a researcher is fired
  • 🤔[1/25/23] Teaching computers to think in abstractions
  • 🎩[1/23/23] The secret sauce behind ChatGPT
  • 📸[1/20/23] FlashAttention challenges ML researchers to think about systems-level improvements
  • ✂️[1/18/23] Make models smarter not larger, with data pruning
  • 🙅[1/16/23] DeepMind attempts to make AI that can do anything
  • 🐣[1/8/23] Chinchilla is the strongest animal/model in the world
  • ⬇️[1/5/23] Gradient descent-ing gradient descent
  • 🥘[1/3/23] Cramming: Training a Language Model on a Single GPU in One Day
  • 🗃️[1/1/23] A Neural Corpus Indexer for Document Retrieval
  • 👋[12/27/22] Can We Teach Machines to Act Like Humans? (And Should We?)
Powered by GitBook