Skip to content
Phil's Library

Eight things to know about large language models

As of mid-2023 from Samuel R. Bowman (Eight Things to Know about Large Language Models (nyu.edu)):

  1. LLMs predictably get more capable with increasing investment, even without targeted innovation.
  2. Many important LLM behaviors emerge unpredictably as a byproduct of increasing investment.
  3. LLMs often appear to learn and use representations of the outside world.
  4. There are no reliable techniques for steering the behavior of LLMs.
  5. Experts are not yet able to interpret the inner workings of LLMs.
  6. Human performance on a task isn’t an upper bound on LLM performance.
  7. LLMs need not express the values of their creators nor the values encoded in web text.
  8. Brief interactions with LLMs are often misleading.