AI ALIGNMENT FORUM
Wikitags
AF

Subscribe
Discussion0
1

Exercises / Problem-Sets

Subscribe
Discussion0
1
Written by Bird Concept, Yoav Ravid last updated 9th Feb 2021

This tag collects posts with concrete exercises. Problems that have solutions (or least some clear feedback loop). Things that you can attempt yourself in order to learn and grow. 

Related Pages: Games (posts describing)

Posts tagged Exercises / Problem-Sets
29Reframing Impact
Alex Turner
5y
4
23Topological Fixed Point Exercises
Scott Garrabrant, Sam Eisenstat
7y
40
57Alignment research exercises
Richard Ngo
3y
7
32Interpretability with Sparse Autoencoders (Colab exercises)
CallumMcDougall
2y
0
19Deducing Impact
Alex Turner
6y
18
22Value Impact
Alex Turner
6y
3
18Game Theory without Argmax [Part 1]
Cleo Nardo
2y
1
22World State is the Wrong Abstraction for Impact
Alex Turner
6y
6
27Mech Interp Puzzle 1: Suspiciously Similar Embeddings in GPT-Neo
Neel Nanda
2y
2
17Infra-Exercises, Part 1
Diffractor, Jack Parker, Connall Garrod
3y
1
17Deep learning curriculum for large language model alignment
Jacob Hilton
3y
3
22Attainable Utility Landscape: How The World Is Changed
Alex Turner
5y
5
17Mech Interp Puzzle 2: Word2Vec Style Embeddings
Neel Nanda
2y
2
16Fixed Point Exercises
Scott Garrabrant
7y
0
23An Exercise to Build Intuitions on AGI Risk
Lauro Langosco
2y
3
Load More (15/16)
Add Posts