rational
Issue #212: Full List
1 May, 2022 // View curated list
# Instrumental
Slack gives you space to notice/reflect on subtle things // Raemon, 1 min Favorite
Saying no to the Appleman // johannes-c-mayer, 3 min
21 on 21 // amir-gamil, 5 min
On Tables and Happiness // alexander-1, 2 min
3-bit filters // iivonen, 2 min
# Epistemic
Why pessimism sounds smart // jasoncrawford, 1 min Favorite
Salvage Epistemology // jimrandomh, 1 min
Facts Matter // [email protected], 3 min
I Think Therefore Someone Is Or Was? // Matt Goldwater, 1 min
A Parable Of Explainability // George3d6, 6 min
# Ai
dalle2 comments // nostalgebraist, 17 min Favorite
Why hasn't deep learning generated significant economic value yet? // Alex_Altair, 1 min
[Linkpost] New multi-modal Deepmind model fusing Chinchilla with images and videos // p.b., 1 min
Key questions about artificial sentience: an opinionated guide // Robbo, 22 min
How Might an Alignment Attractor Look like? // shminux, 1 min
Quick Thoughts on A.I. Governance // NicholasKross, 2 min
SERI ML Alignment Theory Scholars Program 2022 // ryankidd44, 3 min
Why Copilot Accelerates Timelines // mtrazzi, 8 min
If you’re very optimistic about ELK then you should be optimistic about alignment // samuel-marks, 4 min
[Intro to brain-like-AGI safety] 13. Symbol grounding & human social instincts // steve2152, 18 min
Framings of Deceptive Alignment // peterbarnett, 5 min
Learning the smooth prior // Geoffrey Irving, 14 min
Law-Following AI 1: Sequence Introduction and Structure // Cullen_OKeefe, 10 min
Naive comments on AGIlignment // Ericf, 1 min
What is a training "step" vs. "episode" in machine learning? // Evan R. Murphy, 1 min
Note-Taking without Hidden Messages // Hoagy, 4 min
Slides: Potential Risks From Advanced AI // alenglander, 1 min
Examining Evolution as an Upper Bound for AGI Timelines // meanderingmoose, 10 min
What is being improved in recursive self improvement? // conor-sullivan, 1 min
Law-Following AI 2: Intent Alignment + Superintelligence → Lawless AI (By Default) // Cullen_OKeefe, 7 min
Law-Following AI 3: Lawless AI Agents Undermine Stabilizing Agreements // Cullen_OKeefe, 3 min
# Meta-ethics
Why I'm Not a Utilitarian in Modern America // DanB, 10 min
# Longevity
We transhumanists want immortality... But is it really possible? // superads91, 1 min
# Decision theory
Nuclear Energy - Good but not the silver bullet we were hoping for // marius-hobbhahn, 18 min
How good is spending? // tryactions, 1 min
Do FDT (or similar) recommend reparations? // capybaralet, 1 min
Quadratic voting with automatic collusion? // GuySrinivasan, 1 min
# Math and cs
Continental Philosophy as Undergraduate Mathematics // jan-2, 11 min
Make a neural network in ~10 minutes // Arjun Yadav, 4 min
# Books
Book Review: A Clinical Introduction To Lacanian Psychoanalysis // Scott Alexander, 22 min
# Ea
Increasing Demandingness in EA // jkaufman, 3 min
# Culture war
Virtue signaling is sometimes the best or the only metric we have // Holly_Elmore, 6 min
Ukraine Post #11: Longer Term Predictions // Zvi, 13 min
Covid 4/28/22: Take My Paxlovid, Please // Zvi, 9 min
Highlights From The Comments On Xi Jinping // Scott Alexander, 15 min
# Fun
What is the solution to the Alignment problem? // Algon, 1 min
# Misc
The Game of Masks // Hivewired, 13 min
Intuitions about solving hard problems // ricraz, 6 min
Two Prosocial Rejection Norms // Emrik North, 2 min
Rationality Dojo // lsusr, 1 min
The Meaning of Life // Robin Hanson, 1 min
# Podcasts
#128 - Chris Blattman on the five reasons wars happen // , 166 min
# Rational fiction
The case for turning glowfic into Sequences // thomas-kwa, 5 min
Dath Ilan vs. Sid Meier's Alpha Centauri: Pareto Improvements // David Udell, 2 min
# Videos of the week
5 Promising Factors Propelling Climate Action | Gabriel Kra | TED Countdown // TED, 11 min