rationalnewsletter

Issue #194: Full List

Meta (Facebook) is using AI to bring children’s drawings to life. // twitter.com

# Coronavirus

Omicron Post #4 // Zvi, 19 min

Omicron Post #5 // Zvi, 16 min

Interpreting the Biobot Spike // jkaufman, 1 min

Covid 12/9: Counting Down the Days // Zvi, 14 min

COVID and the holidays // Connor_Flexman, 10 min

EA Dinner Covid Logistics // jkaufman, 1 min

Diseasonality // Scott Alexander, 10 min

# Instrumental

Dear Self; We Need To Talk About Social Media // pktechgirl, 12 min

Stop arbitrarily limiting yourself // unoptimal, 3 min

Ordering yourself around with an app // bfinn, 4 min

Anxiety and computer architecture // adamzerner, 3 min

# Epistemic

Randomness in Science // rogersbacon, 10 min

Anti-correlated causation // AllAmericanBreakfast, 4 min

Declustering, reclustering, and filling in thingspace // Stuart_Armstrong, 3 min

Explicit model visualizations // dorian-stern-vukotic, 14 min

What makes for a good "argument"? (Request for thoughts and comments) // simon-dedeo, 2 min

# Ai

The Plan // johnswentworth, 17 min

Deepmind's Gopher--more powerful than GPT-3 // hath

Interpreting Yudkowsky on Deep vs Shallow Knowledge // adamShimi, 29 min

Theoretical Neuroscience For Alignment Theory // cameron-berg, 29 min

ML Alignment Theory Program under Evan Hubinger // oliver-zhang, 2 min

There is essentially one best-validated theory of cognition. // abramdemski, 3 min

[Linkpost] Chinese government's guidelines on AI // RomanS, 1 min

Let's buy out Cyc, for use in AGI interpretability systems? // steve2152, 2 min

Exterminating humans might be on the to-do list of a Friendly AI // RomanS, 2 min

Considerations on interaction between AI and expected value of the future // beth-barnes, 4 min

Interviews on Improving the AI Safety Pipeline // Chris_Leong, 14 min

Modeling Failure Modes of High-Level Machine Intelligence // ben-cottier, 15 min

[MLSN #2]: Adversarial Training // daniel-hendrycks, 3 min

Introduction to inaccessible information // ryankidd44, 9 min

Understanding Gradient Hacking // peterbarnett, 36 min

Considerations on interaction between AI and EV of the future // beth-barnes, 4 min

What role should evolutionary analogies play in understanding AI takeoff speeds? // anson.ho, 48 min

What alignment-related concepts should be better known in the broader ML community? // Lauro Langosco, 1 min

Some thoughts on why adversarial training might be useful // beth-barnes, 2 min

A Framework to Explain Bayesian Models // Jsevillamol, 10 min

Are limited-horizon agents a good heuristic for the off-switch problem? // yonadav-shavit, 1 min

Finding the multiple ground truths of CoinRun and image classification // Stuart_Armstrong, 2 min

Magna Alta Doctrina // jacob_cannell, 34 min

Seeing the Invisible (And How to Think About Machine Learning) // fidnie, 4 min

More Christiano, Cotra, and Yudkowsky on AI progress // Rob Bensinger, 49 min

# Meta-ethics

Extrinsic and Intrinsic Moral Frameworks // lsusr, 2 min

# Anthropic

Are big brains for processing sensory input? // lsusr, 3 min

Implications of the Grabby Aliens Model // harsimony, 2 min

Coming Commitment Conflicts // Robin Hanson, 1 min

On Evolved Values // Robin Hanson, 4 min

# Decision theory

Retail Investor Advantages // leogao, 1 min

What would be the pros and cons of a government-backed, property-based cryptocurrency? // Asgård, 1 min

What on Earth is a Series I savings bond? // rossry, 9 min

Does Georgism Work, Part 3: Can Unimproved Land Value be Accurately Assessed Separately From Buildings? // Scott Alexander, 34 min

Does Georgism Work? Part 2: Can Landlords Pass Land Value Tax on to Tenants? // Scott Alexander, 22 min

Does Georgism Work? Is Land Really A Big Deal? // Scott Alexander, 45 min

# Math and cs

The Promise and Peril of Finite Sets // davidad, 7 min

A Possible Resolution To Spurious Counterfactuals // JoshuaOSHickman, 4 min

Transforming myopic optimization to ordinary optimization - Do we want to seek convergence for myopic optimization problems? // tailcalled, 6 min

Combining Forecasts // jsteinhardt, 7 min

# Relationships

What have your romantic experiences with non-EAs/non-Rationalists been like? // BossSleepy, 1 min

# Community

LessWrong discussed in New Ideas in Psychology article // rogersbacon, 4 min

Life, struggle, and the psychological fallout from COVID // alexflint, 9 min

The Last Questions (part 1) // rogersbacon, 5 min

# Misc

Leaving Orbit // RobbBB, 1 min

The end of Victorian culture, part I: structural forces // david-hugh-jones, 4 min

Reasons to act according to the free will paradigm? // maciej-jalocha, 1 min

Nonverbal thinkers: how do you experience your inner critic? // phoenix-eliot, 1 min

Model City Monday 12/6/21 // Scott Alexander, 11 min

# Podcasts

c36: Script Draft 1, Beat 1 // Constellation, 37 min

Humanity on the precipice (Toby Ord) // Rationally Speaking, 68 min

# Rational fiction

Counting Lightning // Jsevillamol, 7 min

# Videos of the week

How to deal with your insomnia — and finally get to sleep | Sleeping with Science // TED, 1 min