rational
Issue #218: Full List
26 June, 2022 // View curated list
# Instrumental
Air Conditioner Test Results & Discussion // johnswentworth, 7 min
[Link] Childcare : what the science says // Gunnar_Zarncke, 1 min
How do I use caffeine optimally? // randomstring, 1 min
Hydrophobic Glasses Coating Review // jkaufman, 1 min
Evaluating a Corsi-Rosenthal Filter Cube // jkaufman, 1 min
# Epistemic
Steam // abramdemski, 5 min
Cracks in the Wall, Part I: The Conscious // silo, 15 min
What I mean by the phrase “getting intimate with reality” // Luise, 2 min
What I mean by the phrase "taking ideas seriously" // Luise, 1 min
Getting stuck in local minima // louis-beaumont, 1 min
How to Visualize Bayesianism // David Udell, 4 min
# Ai
Where I agree and disagree with Eliezer // paulfchristiano, 24 min
Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment // elspood, 8 min
AI-Written Critiques Help Humans Notice Flaws // paulfchristiano, 3 min
Conversation with Eliezer: What do you want the system to do? // akash-wasil, 3 min
The inordinately slow spread of good AGI conversations in ML // RobbBB, 9 min
Let's See You Write That Corrigibility Tag // Eliezer_Yudkowsky, 1 min
A Quick List of Some Problems in AI Alignment As A Field // NicholasKross, 7 min
What’s the contingency plan if we get AGI tomorrow? // yitz, 1 min
AI Training Should Allow Opt-Out // alyssavance, 7 min
[Link] OpenAI: Learning to Play Minecraft with Video PreTraining (VPT) // alenglander, 1 min
Linkpost: Robin Hanson - Why Not Wait On AI Risk? // yair-halberstadt, 1 min
Half-baked AI Safety ideas thread // alenglander, 1 min
20 Critiques of AI Safety That I Found on Twitter // dkirmani, 1 min
Causal confusion as an argument against the scaling hypothesis // RobertKirk, 22 min
Parable: The Bomb that doesn't Explode // conor-sullivan, 2 min
[Link-post] On Deference and Yudkowsky's AI Risk Estimates // bmg, 1 min
Lamda is not an LLM // Kevin, 1 min
Google's new text-to-image model - Parti, a demonstration of scaling benefits // kunvar-thaman, 1 min
Key Papers in Language Model Safety // Aidan O'Gara, 25 min
Updated Deference is not a strong argument against the utility uncertainty approach to alignment // ivan-vendrov, 4 min
Reflection Mechanisms as an Alignment target: A survey // marius-hobbhahn, 17 min
[Link] Adversarially trained neural representations may already be as robust as corresponding biological neural representations // Gunnar_Zarncke, 1 min
How large of an army could you make with the first 'human-level' AGIs? // joshua-clymer, 8 min
Is CIRL a promising agenda? // Chris_Leong, 1 min
Do you consider your current, non-superhuman self aligned with “humanity” already? // Rana Dexsin, 1 min
Do alignment concerns extend to powerful non-AI agents? // Ozyrus, 1 min
AI misalignment risk from GPT-like systems? // fiso, 1 min
On corrigibility and its basin // donald-hobson, 2 min
Conditioning Generative Models // adam-jermyn, 12 min
Should any human enslave an AGI system? // AlignmentMirror, 1 min
What is the difference between AI misalignment and bad programming? // puzzleGuzzle, 1 min
Debating Whether AI is Conscious Is A Distraction from Real Problems // sidhe_they, 1 min
Dependencies for AGI pessimism // yitz, 1 min
Raphaël Millière on Generalization and Scaling Maximalism // mtrazzi, 4 min
A Toy Model of Gradient Hacking // Oam Patel, 5 min
Mitigating the damage from unaligned ASI by cooperating with aliens that don't exist yet // MSRayne, 7 min
SunPJ in Alenia // florian-habermacher, 10 min
[LQ] Some Thoughts on Messaging Around AI Risk // DragonGod, 7 min
Half-baked alignment idea: training to generalize // aaronb50, 4 min
An AI defense-offense symmetry thesis // chrisvm, 3 min
Is the study of AI an infohazard? // blackstampede, 1 min
What if the best path for a person who wants to work on AGI alignment is to join Facebook or Google? // dbasch, 1 min
Getting from unaligned to aligned (AGI-assisted alignment Part 1) // tor-okland-barstad, 12 min
What is the most probable AI? // Zeruel017, 3 min
AGI-assisted alignment (Part 1: Introduction) // tor-okland-barstad, 12 min
Updated Deference is not evidence against the utility uncertainty approach to alignment // ivan-vendrov, 4 min
Loose thoughts on AGI risk // yitz, 1 min
The Limits of Automation // milkandcigarettes, 6 min
Confusion about neuroscience/cognitive science as a danger for AI Alignment // samuel-nellessen, 3 min
Parti, a demonstration of scaling // kunvar-thaman, 1 min
How easy/fast is it for a AGI to hack computers/a human brain? // sharmake-farah, 1 min
Are we there yet? // theflowerpot, 1 min
Specific problems with specific animal comparisons for AI policy // TrevorWiesinger, 2 min
What are the best "policy" approaches in worlds where alignment is difficult? // liam-alexander, 1 min
Why Not Wait On AI Risk? // Robin Hanson, 6 min
# Meta-ethics
Re An Accused, Tell The Truth // Robin Hanson, 3 min
You Owe Your Parents Grandkids // Robin Hanson, 3 min
# Longevity
Is there a master timekeeper, upstream of the methylation clock? // Josh Mitteldorf, 11 min
# Decision theory
ETH is probably undervalued right now // adrian-arellano-davin, 1 min
How "should" counterfactual prediction markets work? // edward-pierzchalski, 1 min
Quick Summaries of Two Papers on Kant and Game Theory // Erich_Grunewald, 5 min
The Malthusian Trap: An Extremely Short Introduction // Davis Kedrosky, 7 min
# Math and cs
Identification of Natural Modularity // LosPolloFowler, 8 min
Worked Examples of Shapley Values // lalaithion, 9 min
# Books
Book review: The Passenger by Lisa Lutz // KatjaGrace, 1 min
Your Book Review: Public Choice Theory And The Illusion Of Grand Strategy // Scott Alexander, 28 min
Book Review: San Fransicko // Scott Alexander, 94 min
# Ea
Nonprofit Boards are Weird // HoldenKarnofsky, 24 min
# Relationships
Relationship Advice Repository // Ruby, 46 min
# Community
Some reflections on the LW community after several months of active engagement // M. Y. Zuo, 5 min
Announcing the DWATV Discord // Zvi, 1 min
Have The Effective Altruists And Rationalists Brainwashed Me? // Matt Goldwater, 12 min
# Culture war
Parliaments without the Parties // yair-halberstadt, 2 min
Politics is the Mind Killer. But is it getting worse? // TrevorWiesinger, 1 min
How do states respond to changes in nuclear risk // NathanBarnard, 6 min
# Art
Solstice Movie Review: Summer Wars // JohnBuridan, 1 min
# Misc
Make learning a reality // dalton-mabery, 1 min
Building an Epistemic Status Tracker // rcu, 1 min
[Linkpost] The importance of stupidity in scientific research // Pattern
Is This Thing Sentient, Y/N? // Thane Ruthenis, 7 min
Hebbian Learning Is More Common Than You Think // aleksi-liimatainen, 1 min
What is a Life? // Venkatesh Rao, 22 min
# Podcasts
Announcing the LessWrong Curated Podcast // Benito, 1 min
# Rational fiction
Dagger of Detect Evil // lsusr, 3 min
# Videos of the week
DeepMind: The Quest to Solve Intelligence // Neura Pod – Neuralink, 53 min