ð± Skyspace3.0
Search
Search
Search
Dark mode
Light mode
Explorer
0stack
unreadable-notes
2024-06-21
2024-06-25
2024-06-27
2024-07-24
Borůvka
Expansion Review
hashtable without hash functions
network decompositions
routing
a note on effective altruism + et al.
A simple alignment proposal
actual explanation
addictive technologies are harmful
algorithm class notes
alignment meta-research algorithm
arena notes
backdoors and deceptive alignment
Brainstorming Some Open Questions
bucket list of learning exercises
CAIP model organism proposal
Can I enjoy arbitrary things?
Causal Scrubbing Notes
crypto primitives
deep learning class -- some things I've learned
Do you have the Markov property?
dont look up
double standard
Emotional Health in the face of the AI Situation
Ethics of Computing Essay 1
finding c4s
fine tuning
good arguments
inference
intro-to-rl
Inverse Reward Design -- paper summary
mildly hot takes
mnist
OLD --- ARC formal verification notes
on feelings
open-ness
physics notes
ridiculous BFS
Risks from AI -- elevator pitch
some ml projects and reflection
some permutation avoidance notes
some problems from my friends
some random super old alignment notes
superposition
taking life seriously
The Inner Alignment Problem
the world is full of allies
The Wrong Person
Thinking about people's reactions to AI xrisk
two mistakes in my plans for mitigating xrisk
What could go wrong?
What Should We Do About the xRisk Posed by ASI?
wins
worrying about giving offense
1research
backdoors take 2
concrete questions
LPE Agenda
MAD Agenda
refuting NCP
safe distillation
Solving AI Safety from 1st principles
2notes
cryptographic proofs
iterated amplification
low vs high stakes alignment
online convex optimization
*log
5 years
100% is easier than 99%
accept the truth
acting NOW
AI xrisk
akrasia
avoid_discomfort.cpp
be specific
Can I change my objective function? Should I?
change is atomic
cognitive distortion list
consciousness
contact
cooking
determinism is useless
existence
existence of objective function
Favorite Endeavors by Aesthetics
flake
food-water
fun activity ideas
good problems
good subgoals
Goodhart's law
goodness(universe)
how I want to spend my life
human compute is scarce
intention
is judging people a good idea?
justification
laughing at serious things
listening
live research options
mind reading
motivated reasoning
not fail with abandon
nukes xrisk thoughts
OLD AI xrisk argument
on writing, blogging and being opinionated
outer loop, inner loop
pascal-wager
point of research
prediction vs explanation
press the button
procrastinating choices
recovering from being tired when working
responsibility
science AI xrisk article
self betrayal
sleep
social
speak the truth?
stimuli
taboo
taking social initiative
talking to people
Terms for others in my utility function
trivia
walking
Want to X or want to have X'd
What do I need money for?
what influence do perceived expectations have on me?
Will humans beat death in the next 30 years?
win-the-lottery-utility
working healthily
wrong exists
your work is not your worth
Home
â¯
listening
listening
Jan 26, 2025
1 min read
Q: How should you listen to people?
maintain eye contact
ask questions (when appropriate)
Graph View
Backlinks
Favorite Endeavors by Aesthetics
talking to people
walking