Epistemic bottlenecks
2021-08-24 — 2024-10-04
Wherein the transmissibility of knowledge is examined, transmission costs are framed through a Kolmogorov‑style minimal description, and the capacity of LLMs to teach other models is considered.
Is the Bitter lesson about minimizing transmission costs?
What is the transmissibility of knowledge? What is knowledge about? Can an LLM teach? (apparently yes?) Can an LLM teach LLMs? (apparently yes?)
1 Incoming
Blurry JPEG or Frozen Concentrate
What we want is a description of a program \(p\) that corresponds to a set of possible Wikipedia articles, of which the real article is a random example of this set. An ideal version of ChatGPT would choose a random article from this set. Dall-E, generative AI for art, works a similar way, creating art that is a random example of what art might have been.
In terms of Kolmogorov complexity, this corresponds to the Kolmogorov Structure Function, basically the smallest program \(p\) such that \(p\) describes a set \(S\) of size \(m\) that contains \(x\). with \(|p| + \log m \approx K(x)\). The string \(x\) is just a random element of \(S\), you can get a string like it by picking an element of \(S\) at random.