LESSWRONG
LW

1188
Wikitags

Has Diagram

Edited by Gunnar_Zarncke last updated 29th Apr 2023

This tag is used to indicate that the post contains diagrams. This may be useful to quickly find such posts, or to exclude them in case you are visually impaired. 

Subscribe
Discussion
Subscribe
Discussion
Posts tagged Has Diagram
228What are the results of more parental supervision and less outdoor play?
juliawise
2y
31
151Using axis lines for good or evil
dynomight
2y
39
513How much do you believe your results?
Eric Neyman
2y
18
491Being the (Pareto) Best in the World
johnswentworth
6y
61
366A deep critique of AI 2027’s bad timeline models
titotal
4mo
39
226Self-Other Overlap: A Neglected Approach to AI Alignment
Ω
Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena, Cameron Berg, Trent Hodgeson
1y
Ω
51
173Bayes' Theorem Illustrated (My Way)
komponisto
15y
195
163[Intro to brain-like-AGI safety] 1. What's the problem & Why work on it now?
Ω
Steven Byrnes
4y
Ω
19
162Reducing LLM deception at scale with self-other overlap fine-tuning
Ω
Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Cameron Berg, Mike Vaiana, Trent Hodgeson
7mo
Ω
46
132Induction heads - illustrated
CallumMcDougall
3y
12
108Demystifying "Alignment" through a Comic
milanrosko
1y
19
105I turned decision theory problems into memes about trolleys
Tapatakt
1y
23
100Machine Learning Analogy for Meditation (illustrated)
abramdemski
7y
48
95[Intro to brain-like-AGI safety] 3. Two subsystems: Learning & Steering
Ω
Steven Byrnes
4y
Ω
3
94Towards a Less Bullshit Model of Semantics
Ω
johnswentworth, David Lorell
1y
Ω
44
Load More (15/49)
Add Posts