Modified: February 13, 2023
GPT
This page is from my personal notes, and has not been specifically reviewed for public consumption. It might be incomplete, wrong, outdated, or stupid. Caveat lector.Links to this note
value learning
Notes on the Alignment Forum's Value Learning sequence curated by Rohin Shah. ambitious value learning : the idea of learning 'the human…
research idea
This note lists some ideas and directions for research I'm interested in or excited about. Some are more fleshed out than others, some more…
tokenize
How should a machine learning model represent text? Word-level and character-level features are obvious options, but both have drawbacks…
transformers with memory
Incorporating explicit memory and retrieval seems pretty clearly like the next frontier in language modeling and AI more broadly. We have…
transformer
The core of the transformer architecture is multi-headed [ attention ]. The transformer block consists of a multi-headed attention layer…
safe objective
Language is a really natural way to tell AI systems what we want them to do. Some current examples: [ GPT ]-3 and successors (InstructGPT…
explicit models of uncertainty
(note: this is dancing around the issues around why I think [ probabilistic programming is not AI research ], even if it will be a…
phase change hypothesis
(see also: [ large models ]) There's a viewpoint that neural nets just memorize the training data, so the more training data you have, the…
large models
If you believe that neural nets basically just memorize the training data, then training larger and larger models is hopeless. The…
AI for math
Doing [ math ] seems like a really promising area for AI. And by 'math' I mean math research (not arithmetic, which computers are already…
data efficiency
Current (2021) deep networks require huge datasets in order to [ generalization|generalize ]. But we know that humans can do one-shot…