Build your own agents which are controlled by LLMs | Hacker News
that people—or, if you like, automata, algorithms—can and do act in situations that are not well defined.
W. Brian Arthur • Complexity Economics: Proceedings of the Santa Fe Institute's 2019 Fall Symposium
- What a modern LLM does during training is, essentially, very very quickly skim the textbook, the words just flying by , not spending much brain power on it.
- Rather, when you or I read that math textbook, we read a couple pages slowly; then have an internal monologue about the material in our heads and talk about it with a few study-buddies; read an
SITUATIONAL AWARENESS - The Decade Ahead • I. From GPT-4 to AGI: Counting the OOMs
MLEs are happy to delegate experiment tracking and execution work to ML experiment execution frameworks, such as Weights & Biases 3 , but prefer to choose subsequent experiments themselves. To be able to make informed choices of subsequent experiments to run, MLEs must maintain awareness of what they have tried and what they haven’t (Lg2 calls ... See more
Shreya Shankar • "We Have No Idea How Models will Behave in Production until Production": How Engineers Operationalize Machine Learning.
The repertoire generation loop is more or less a statement of the scientific method, in which we create new hypotheses based on observation and synthesis, design experiments to test these hypotheses, and then update or discard our theories (which form part of our orientation) based on the results of the experiment.