LessWrong (30+ Karma)
By LessWrong
Listen to a podcast, please open Podcast Republic app. Available on Google Play Store and Apple App Store.
Image by LessWrong
Category: Technology
Open in Apple Podcasts
Open RSS feed
Open Website
Rate for this podcast
Subscribers: 3
Reviews: 0
Episodes: 250
Description
Audio narrations of LessWrong posts.
| Episode | Date |
|---|---|
|
“The 80/20 playbook for mitigating AI scheming risks in 2025” by Charbel-Raphaël
|
Jun 01, 2025 |
|
“The best approaches for mitigating ‘the intelligence curse’ (or gradual disempowerment); my quick guesses at the best object-level interventions” by ryan_greenblatt
|
May 31, 2025 |
|
“‘GiveWell for AI Safety’: Lessons learned in a week” by Lydia Nottingham
|
May 31, 2025 |
|
“Letting Kids Be Kids” by Zvi
|
May 30, 2025 |
|
“Orphaned Policies (Post 5 of 6 on AI Governance)” by Mass_Driver
|
May 30, 2025 |
|
“Do you even have a system prompt? (PSA)” by Croissanthology
|
May 30, 2025 |
|
[Linkpost] “Incorrect Baseline Evaluations Call into Question Recent LLM-RL Claims” by shash42
|
May 30, 2025 |
|
“CFAR is running an experimental mini-workshop (June 2-6, Berkeley CA)!” by Davis_Kingsley
|
May 30, 2025 |
|
“AI #118: Claude Ascendant” by Zvi
|
May 29, 2025 |
|
“Gradual Disempowerment: Concrete Research Projects” by Raymond Douglas
|
May 29, 2025 |
|
“Truth or Dare” by Duncan Sabien (Inactive)
|
May 29, 2025 |
|
“The Best Way to Align an LLM: Inner Alignment is Now a Solved Problem?” by RogerDearnaley
|
May 29, 2025 |
|
“LessWrong Feed [new, now in beta]” by Ruby
|
May 28, 2025 |
|
“Shift Resources to Advocacy Now (Post 4 of 6 on AI Governance)” by Mass_Driver
|
May 28, 2025 |
|
[Linkpost] “If you’re not sure how to sort a list or grid—seriate it!” by gwern
|
May 28, 2025 |
|
“Beware the Moral Homophone” by ymeskhout
|
May 28, 2025 |
|
“Briefly analyzing the 10-year moratorium amendment” by RobertM
|
May 28, 2025 |
|
“What We Learned from Briefing 70+ Lawmakers on the Threat from AI” by leticiagarcia
|
May 28, 2025 |
|
“Requiem for the hopes of a pre-AI world” by Mitchell_Porter
|
May 27, 2025 |
|
“Season Recap of the Village: Agents raise $2,000” by Shoshannah Tekofsky
|
May 27, 2025 |
|
“Association taxes are collusion subsidies” by KatjaGrace
|
May 27, 2025 |
|
“Socratic Persuasion: Giving Opinionated Yet Truth-Seeking Advice” by Neel Nanda
|
May 27, 2025 |
|
[Linkpost] “Formalizing Embeddedness Failures in Universal Artificial Intelligence” by Cole Wyeth
|
May 27, 2025 |
|
“Claude 4 You: The Quest for Mundane Utility” by Zvi
|
May 27, 2025 |
|
“New website analyzing AI companies’ model evals” by Zach Stein-Perlman
|
May 26, 2025 |
|
“New scorecard evaluating AI companies on safety” by Zach Stein-Perlman
|
May 26, 2025 |
|
“Alignment Proposal: Adversarially Robust Augmentation and Distillation” by Cole Wyeth, abramdemski
|
May 26, 2025 |
|
[Linkpost] “Priming effects are fake, but framing effects are real” by Matrice Jacobine
|
May 25, 2025 |
|
“Meditations on Doge” by Martin Sustrik
|
May 25, 2025 |
|
“Claude 4 You: Safety and Alignment” by Zvi
|
May 25, 2025 |
|
“It’s hard to make scheming evals look realistic” by Igor Ivanov, dan_moken
|
May 25, 2025 |
|
“That’s Not How Epigenetic Modifications Work” by johnswentworth
|
May 24, 2025 |
|
“AI #117: OpenAI Buys Device Maker IO” by Zvi
|
May 24, 2025 |
|
“Learning (more) from horse employment history” by Tim H
|
May 23, 2025 |
|
“Reward button alignment” by Steven Byrnes
|
May 23, 2025 |
|
“Mirror Organisms Are Not Immune to Predation” by Matthias Dellago
|
May 23, 2025 |
|
“Anthropic is Quietly Backpedalling on its Safety Commitments” by garrison
|
May 23, 2025 |
|
“We’re Not Advertising Enough (Post 3 of 6 on AI Governance)” by Mass_Driver
|
May 22, 2025 |
|
“Units have more depth than I thought” by Morpheus
|
May 22, 2025 |
|
“Policy recommendations regarding reproductive technology” by TsviBT
|
May 22, 2025 |
|
[Linkpost] “Claude 4” by Zach Stein-Perlman
|
May 22, 2025 |
|
“Can We Naturalize Moral Epistemology?” by tylermjohn
|
May 22, 2025 |
|
[Linkpost] “President of European Commission expects human-level AI by 2026” by sanyer
|
May 22, 2025 |
|
“Google I/O Day” by Zvi
|
May 22, 2025 |
|
“The Need for Political Advertising
(Post 2 of 6 on AI Governance)” by Mass_Driver
|
May 22, 2025 |
|
“Unexploitable search: blocking malicious use of free parameters” by Benjamin Hilton, Jacob Pfau, Geoffrey Irving
|
May 22, 2025 |
|
“Sleep need reduction therapies” by harsimony
|
May 21, 2025 |
|
“The stakes of AI moral status” by Joe Carlsmith
|
May 21, 2025 |
|
“The Codex of Ultimate Vibing” by Zvi
|
May 21, 2025 |
|
“Off-ramps of the Geopolitical Singularity” by Nikola Jurkovic
|
May 20, 2025 |
|
[Linkpost] “Gemini Diffusion: watch this space” by Yair Halberstadt
|
May 20, 2025 |
|
“Winning the power to lose” by KatjaGrace
|
May 20, 2025 |
|
“Semen and Semantics: Understanding Porn with Language Embeddings” by future_detective
|
May 20, 2025 |
|
“America Makes AI Chip Diffusion Deal with UAE and KSA” by Zvi
|
May 20, 2025 |
|
“Thoughts on ‘Antiqua et nova’ (Catholic Church’s AI statement)” by jchan
|
May 20, 2025 |
|
[Linkpost] “One Year in DC” by tlevin
|
May 19, 2025 |
|
[Linkpost] “[Funded Fellowship] AI for Human Reasoning Fellowship, with the Future of Life Foundation” by Oliver Sourbut, Ben Goldhaber
|
May 19, 2025 |
|
“A widely shared AI productivity paper was retracted, is possibly fraudulent” by titotal
|
May 19, 2025 |
|
“Dreams of Ideas” by Joseph Miller
|
May 19, 2025 |
|
“Google Logo Ligature Bug” by jefftk
|
May 18, 2025 |
|
“D&D.Sci: The Choosing Ones” by abstractapplic
|
May 18, 2025 |
|
“Book Review: The Art of Happiness” by Screwtape
|
May 18, 2025 |
|
“What OpenAI Told California’s Attorney General” by garrison
|
May 18, 2025 |
|
“time is event based” by thiccythot
|
May 17, 2025 |
|
“Events: Debate & Fiction Project” by abramdemski
|
May 17, 2025 |
|
“How Fast Can Algorithms Advance Capabilities? | Epoch Gradient Update” by henryj
|
May 17, 2025 |
|
“Management is the Near Future” by jefftk
|
May 17, 2025 |
|
[Linkpost] “Social Anxiety Isn’t About Being Liked” by Chipmonk
|
May 17, 2025 |
|
“Problems with Instruction Following as an Alignment Target” by Seth Herd
|
May 16, 2025 |
|
“Regarding South Africa” by Zvi
|
May 16, 2025 |
|
“Generating the Funniest Joke with RL (according to GPT-4.1)” by agg
|
May 16, 2025 |
|
“AI #116: If Anyone Builds It, Everyone Dies” by Zvi
|
May 16, 2025 |
|
“What does it mean to ‘write like you talk’?” by Arjun Panickssery
|
May 15, 2025 |
|
“Re SMTM: negative feedback on negative feedback” by Steven Byrnes
|
May 15, 2025 |
|
“Moral Obligation and Moral Opportunity” by Alice Blair
|
May 15, 2025 |
|
“Fighting Obvious Nonsense About AI Diffusion” by Zvi
|
May 14, 2025 |
|
“Dodging systematic human errors in scalable oversight” by Benjamin Hilton, Geoffrey Irving
|
May 14, 2025 |
|
“Eliezer and I wrote a book: If Anyone Builds It, Everyone Dies” by So8res
|
May 14, 2025 |
|
“The Best Reference Works for Every Subject” by Parker Conley
|
May 14, 2025 |
|
“LessWrong Community Weekend - Applications are open” by jt
|
May 14, 2025 |
|
“Working through a small tiling result” by James Payor
|
May 14, 2025 |
|
[Linkpost] “October The First Is Too Late” by gwern
|
May 14, 2025 |
|
“Too Soon” by Gordon Seidoh Worley
|
May 13, 2025 |
|
“No-self as an alignment target” by Milan W
|
May 13, 2025 |
|
“AI Doomerism in 1879” by David Gross
|
May 13, 2025 |
|
“A Live Look at the Senate AI Hearing” by Zvi
|
May 13, 2025 |
|
“Political sycophancy as a model organism of scheming” by Alex Mallen, Vivek Hebbar
|
May 12, 2025 |
|
[Linkpost] “Main Insights From The SB-1047 Documentary” by Michaël Trazzi
|
May 12, 2025 |
|
“PSA: The LessWrong Feedback Service” by JustisMills
|
May 12, 2025 |
|
“AIs at the current capability level may be important for future safety work” by ryan_greenblatt
|
May 12, 2025 |
|
“Highly Opinionated Advice on How to Write ML Papers” by Neel Nanda
|
May 12, 2025 |
|
“a confusion about preference orderings” by nostalgebraist
|
May 11, 2025 |
|
“Better Air Purifiers” by jefftk
|
May 11, 2025 |
|
“Glass box learners want to be black box” by Cole Wyeth
|
May 11, 2025 |
|
“It’s Okay to Feel Bad for a Bit” by moridinamael
|
May 11, 2025 |
|
“Consider not donating under $100 to political candidates” by DanielFilan
|
May 11, 2025 |
|
“Attend the 2025 Reproductive Frontiers Summit, June 10-12” by TsviBT, Rachel Reid
|
May 10, 2025 |
|
“Cheaters Gonna Cheat Cheat Cheat Cheat Cheat” by Zvi
|
May 09, 2025 |
|
“Slow corporations as an intuition pump for AI R&D automation” by ryan_greenblatt, elifland
|
May 09, 2025 |
|
“An alignment safety case sketch based on debate” by Benjamin Hilton, Marie_DB, Jacob Pfau, Geoffrey Irving
|
May 09, 2025 |
|
“Interest In Conflict Is Instrumentally Convergent” by Screwtape
|
May 09, 2025 |
|
“Misalignment and Strategic Underperformance: An Analysis of Sandbagging and Exploration Hacking” by Buck, Julian Stastny
|
May 08, 2025 |
|
“Orienting Toward Wizard Power” by johnswentworth
|
May 08, 2025 |
|
“OpenAI Claims Nonprofit Will Retain Nominal Control” by Zvi
|
May 07, 2025 |
|
[Linkpost] “It’s ‘Well, actually...’ all the way down” by benwr
|
May 07, 2025 |
|
“Please Donate to CAIP (Post 1 of 3 on AI Governance)” by Mass_Driver
|
May 07, 2025 |
|
“UK AISI’s Alignment Team: Research Agenda” by Benjamin Hilton, Jacob Pfau, Marie_DB, Geoffrey Irving
|
May 07, 2025 |
|
“Will protein design tools solve the snake antivenom shortage?” by Abhishaike Mahajan
|
May 07, 2025 |
|
“Global Risks Weekly Roundup #18/2025: US tariff shortages, military policing, Gaza famine.” by NunoSempere
|
May 07, 2025 |
|
“Negative Results on Group SAEs” by Josh Engels
|
May 07, 2025 |
|
“Nonprofit to retain control of OpenAI” by Archimedes
|
May 06, 2025 |
|
“Zuckerberg’s Dystopian AI Vision” by Zvi
|
May 06, 2025 |
|
“$500 + $500 Bounty Problem: An (Approximately) Deterministic Maximal Redund Always Exists” by johnswentworth, David Lorell
|
May 06, 2025 |
|
“Five Hinge‑Questions That Decide Whether AGI Is Five Years Away or Twenty” by charlieoneill
|
May 06, 2025 |
|
“GPT-4o Sycophancy Post Mortem” by Zvi
|
May 06, 2025 |
|
[Linkpost] “Tsinghua paper: Does RL Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?” by Thomas Kwa
|
May 05, 2025 |
|
“The Sweet Lesson: AI Safety Should Scale With Compute” by Jesse Hoogland
|
May 05, 2025 |
|
“Interim Research Report: Mechanisms of Awareness” by Josh Engels, Neel Nanda, Senthooran Rajamanoharan
|
May 05, 2025 |
|
“Overview: AI Safety Outreach Grassroots Orgs” by Severin T. Seehrich
|
May 05, 2025 |
|
“Notes on the Long Tasks METR paper, from a HCAST task contributor” by abstractapplic
|
May 05, 2025 |
|
“Why I am not a successionist” by Nina Panickssery
|
May 04, 2025 |
|
“Updates from Comments on ‘AI 2027 is a Bet Against Amdahl’s Law’” by snewman
|
May 04, 2025 |
|
“‘Superhuman’ Isn’t Well Specified” by JustisMills
|
May 04, 2025 |
|
“Interpretability Will Not Reliably Find Deceptive AI” by Neel Nanda
|
May 04, 2025 |
|
“PSA: Before May 21 is a good time to sign up for cryonics” by AlexMennen
|
May 04, 2025 |
|
“The Ukraine War and the Kill Market” by Martin Sustrik
|
May 04, 2025 |
|
“Navigating burnout” by gw
|
May 04, 2025 |
|
“Obstacles in ARC’s agenda: Low Probability Estimation” by David Matolcsi
|
May 03, 2025 |
|
“Obstacles in ARC’s agenda: Mechanistic Anomaly Detection” by David Matolcsi
|
May 03, 2025 |
|
“AI #114: Liars, Sycophants and Cheaters” by Zvi
|
May 03, 2025 |
|
“What’s going on with AI progress and trends? (As of 5/2025)” by ryan_greenblatt
|
May 02, 2025 |
|
“OpenAI Preparedness Framework 2.0” by Zvi
|
May 02, 2025 |
|
“RA x ControlAI video: What if AI just keeps getting smarter?” by Writer
|
May 02, 2025 |
|
“AI Governance to Avoid Extinction: The Strategic Landscape and Actionable Research Questions” by peterbarnett, Aaron_Scher
|
May 02, 2025 |
|
[Linkpost] “Don’t accuse your interlocutor of being insufficiently truth-seeking” by TFD
|
May 02, 2025 |
|
“Anthropomorphizing AI might be good, actually” by Seth Herd
|
May 02, 2025 |
|
“Superhuman Coders in AI 2027 - Not So Fast” by dschwarz, FutureSearch
|
May 01, 2025 |
|
“Slowdown After 2028: Compute, RLVR Uncertainty, MoE Data Wall” by Vladimir_Nesov
|
May 01, 2025 |
|
“Prioritizing Work” by jefftk
|
May 01, 2025 |
|
“How can we solve diffuse threats like research sabotage with AI control?” by Vivek Hebbar
|
May 01, 2025 |
|
“GPT-4o Responds to Negative Feedback” by Zvi
|
May 01, 2025 |
|
“Obstacles in ARC’s agenda: Finding explanations” by David Matolcsi
|
May 01, 2025 |
|
“Can we safely automate alignment research?” by Joe Carlsmith
|
Apr 30, 2025 |
|
“Early Chinese Language Media Coverage of the AI 2027 Report: A Qualitative Analysis” by jeanne_, eeeee
|
Apr 30, 2025 |
|
“Interpreting the METR Time Horizons Post” by snewman
|
Apr 30, 2025 |
|
“Bandwidth Rules Everything Around Me: Oliver Habryka on OpenPhil and GoodVentures” by Elizabeth
|
Apr 29, 2025 |
|
“Misrepresentation as a Barrier for Interp” by johnswentworth, Steve Petersen
|
Apr 29, 2025 |
|
“How to Build a Third Place on Focusmate” by Parker Conley
|
Apr 29, 2025 |
|
“GPT-4o Is An Absurd Sycophant” by Zvi
|
Apr 28, 2025 |
|
“Proceedings of ILIAD: Lessons and Progress” by Alexander Gietelink Oldenziel
|
Apr 28, 2025 |
|
“7+ tractable directions in AI control” by Julian Stastny, ryan_greenblatt
|
Apr 28, 2025 |
|
“My Research Process: Key Mindsets - Truth-Seeking, Prioritisation, Moving Fast” by Neel Nanda
|
Apr 28, 2025 |
|
“Our Reality: A Simulation Run by a Paperclip Maximizer” by James_Miller, avturchin
|
Apr 28, 2025 |
|
[Linkpost] “How people use LLMs” by Elizabeth
|
Apr 28, 2025 |
|
[Linkpost] “The case for multi-decade AI timelines” by Noosphere89
|
Apr 27, 2025 |
|
[Linkpost] “Untitled Draft” by RobertM
|
Apr 27, 2025 |
|
“AI Self Portraits Aren’t Accurate” by JustisMills
|
Apr 27, 2025 |
|
“How I Think About My Research Process: Explore, Understand, Distill” by Neel Nanda
|
Apr 27, 2025 |
|
“What are important UI-shaped problems that Lightcone could tackle?” by Raemon
|
Apr 27, 2025 |
|
“We should try to automate AI safety work asap” by Marius Hobbhahn
|
Apr 26, 2025 |
|
“Worries About AI Are Usually Complements Not Substitutes” by Zvi
|
Apr 26, 2025 |
|
“AI #113: The o3 Era Begins” by Zvi
|
Apr 25, 2025 |
|
“Token and Taboo” by Guive
|
Apr 25, 2025 |
|
“Reward hacking is becoming more sophisticated and deliberate in frontier LLMs” by Kei
|
Apr 25, 2025 |
|
“The Intelligence Curse: an essay series” by L Rudolf L, lukedrago
|
Apr 24, 2025 |
|
[Linkpost] “Modifying LLM Beliefs with Synthetic Document Finetuning” by RowanWang, Johannes Treutlein, Ethan Perez, Fabien Roger, Sam Marks
|
Apr 24, 2025 |
|
“‘The Era of Experience’ has an unsolved technical alignment problem” by Steven Byrnes
|
Apr 24, 2025 |
|
[Linkpost] “My Favorite Productivity Blog Posts” by Parker Conley
|
Apr 24, 2025 |
|
“OpenAI Alums, Nobel Laureates Urge Regulators to Save Company’s Nonprofit Structure” by garrison
|
Apr 24, 2025 |
|
“o3 Is a Lying Liar” by Zvi
|
Apr 23, 2025 |
|
“Putting up Bumpers” by Sam Bowman
|
Apr 23, 2025 |
|
[Linkpost] “Jaan Tallinn’s 2024 Philanthropy Overview” by jaan
|
Apr 23, 2025 |
|
[Linkpost] “To Understand History, Keep Former Population Distributions In Mind” by Arjun Panickssery
|
Apr 23, 2025 |
|
“The EU Is Asking for Feedback on Frontier AI Regulation (Open to Global Experts)—This Post Breaks Down What’s at Stake for AI Safety” by Katalina Hernandez
|
Apr 23, 2025 |
|
“Societal and technological progress as sewing an ever-growing, ever-changing, patchy, and polychrome quilt” by Joel Z. Leibo, Wilcunningham, Seb Krier, Manfred Diaz
|
Apr 22, 2025 |
|
“You Better Mechanize” by Zvi
|
Apr 22, 2025 |
|
“The US Executive vs Supreme Court Deportations Clash” by NunoSempere
|
Apr 22, 2025 |
|
“Accountability Sinks” by Martin Sustrik
|
Apr 22, 2025 |
|
“The Uses of Complacency” by sarahconstantin
|
Apr 22, 2025 |
|
“$500 Bounty Problem: Are (Approximately) Deterministic Natural Latents All You Need?” by johnswentworth, David Lorell
|
Apr 21, 2025 |
|
“Crime and Punishment #1” by Zvi
|
Apr 21, 2025 |
|
“AI 2027 is a Bet Against Amdahl’s Law” by snewman
|
Apr 21, 2025 |
|
“Research Notes: Running Claude 3.7, Gemini 2.5 Pro, and o3 on Pokémon Red” by Julian Bradshaw
|
Apr 21, 2025 |
|
“How Close We Are to a Complete List of Imprinted Genes” by Morpheus
|
Apr 20, 2025 |
|
“Impact, agency, and taste” by benkuhn
|
Apr 20, 2025 |
|
“Is Gemini now better than Claude at Pokémon?” by Julian Bradshaw
|
Apr 20, 2025 |
|
“Why Should I Assume CCP AGI is Worse Than USG AGI?” by Tomás B.
|
Apr 19, 2025 |
|
“o3 Will Use Its Tools For You” by Zvi
|
Apr 19, 2025 |
|
“Scaffolding Skills” by Screwtape
|
Apr 19, 2025 |
|
“What Makes an AI Startup ‘Net Positive’ for Safety?” by jacquesthibs
|
Apr 19, 2025 |
|
“The Russell Conjugation Illuminator” by TimmyM
|
Apr 18, 2025 |
|
“Handling schemers if shutdown is not an option” by Buck
|
Apr 18, 2025 |
|
“Training AGI in Secret would be Unsafe and Unethical” by Daniel Kokotajlo
|
Apr 18, 2025 |
|
“Three Months In, Evaluating Three Rationalist Cases for Trump” by Arjun Panickssery
|
Apr 18, 2025 |
|
“D&D.Sci Tax Day: Adventurers and Assessments” by aphyer
|
Apr 17, 2025 |
|
“Can SAE steering reveal sandbagging?” by jordine, Hoang Khiem, Felix Hofstätter
|
Apr 17, 2025 |
|
“ALLFED emergency appeal: Help us raise $800,000 to avoid cutting half of programs” by denkenberger
|
Apr 17, 2025 |
|
“AI-enabled coups: a small group could use AI to seize power” by Tom Davidson, Lukas Finnveden, rosehadshar
|
Apr 16, 2025 |
|
“Ctrl-Z: Controlling AI Agents via Resampling” by abhatt349, Buck, Adam Kaufman, Cody Rushing, Tyler Tracy
|
Apr 16, 2025 |
|
“OpenAI rewrote its Preparedness Framework” by Zach Stein-Perlman
|
Apr 16, 2025 |
|
“OpenAI #13: Altman at TED and OpenAI Cutting Corners on Safety Testing” by Zvi
|
Apr 16, 2025 |
|
“ASI existential risk: Reconsidering Alignment as a Goal” by habryka
|
Apr 16, 2025 |
|
“Surprising LLM reasoning failures make me think we still need qualitative breakthroughs for AGI” by Kaj_Sotala
|
Apr 15, 2025 |
|
“A Dissent on Honesty” by eva_
|
Apr 15, 2025 |
|
“Map of AI Safety v2” by Bryce Robertson, Søren Elverlin, Melissa Samworth
|
Apr 15, 2025 |
|
“To be legible, evidence of misalignment probably has to be behavioral” by ryan_greenblatt
|
Apr 15, 2025 |
|
“The Bell Curve of Bad Behavior” by Screwtape
|
Apr 15, 2025 |
|
[Linkpost] “The 4-Minute Mile Effect” by Parker Conley
|
Apr 15, 2025 |
|
[Linkpost] “Sentinel’s Global Risks Weekly Roundup #15/2025: Tariff yoyo, OpenAI slashing safety testing, Iran nuclear programme negotiations, 1K H5N1 confirmed herd infections.” by NunoSempere
|
Apr 15, 2025 |
|
“Try training token-level probes” by StefanHex
|
Apr 14, 2025 |
|
“Frontier AI Models Still Fail at Basic Physical Tasks: A Manufacturing Case Study” by Adam Karvonen
|
Apr 14, 2025 |
|
“Four Types of Disagreement” by silentbob
|
Apr 14, 2025 |
|
“One-shot steering vectors cause emergent misalignment, too” by Jacob Dunefsky
|
Apr 14, 2025 |
|
“Vestigial reasoning in RL” by Caleb Biddulph
|
Apr 14, 2025 |
|
“How I switched careers from software engineer to AI policy operations” by Lucie Philippon
|
Apr 13, 2025 |
|
“College Advice For People Like Me” by henryj
|
Apr 13, 2025 |
|
“Steelmanning heuristic arguments” by Dmitry Vaintrob
|
Apr 13, 2025 |
|
“Why does LW not put much more focus on AI governance and outreach?” by Severin T. Seehrich
|
Apr 12, 2025 |
|
“How training-gamers might function (and win)” by Vivek Hebbar
|
Apr 12, 2025 |
|
“Youth Lockout” by Xavi CF
|
Apr 12, 2025 |
|
“Paper” by dynomight
|
Apr 12, 2025 |
|
“OpenAI Responses API changes models’ behavior” by Jan Betley, James Chua
|
Apr 11, 2025 |
|
“Why do misalignment risks increase as AIs get more capable?” by ryan_greenblatt
|
Apr 11, 2025 |
|
“On Google’s Safety Plan” by Zvi
|
Apr 11, 2025 |
|
“Forecasting time to automated superhuman coders [AI 2027 Timelines Forecast]” by elifland, Nikola Jurkovic
|
Apr 11, 2025 |
|
“Reactions to METR task length paper are insane” by Cole Wyeth
|
Apr 11, 2025 |
|
[Linkpost] “Playing in the Creek” by Hastings
|
Apr 10, 2025 |
|
“Disempowerment spirals as a likely mechanism for existential catastrophe” by Raymond D, owencb
|
Apr 10, 2025 |
|
“The case for AGI by 2030” by Benjamin_Todd
|
Apr 10, 2025 |
|
[Linkpost] “New Paper: Infra-Bayesian Decision-Estimation Theory” by Vanessa Kosoy, Diffractor
|
Apr 10, 2025 |
|
“Thoughts on AI 2027” by Max Harms
|
Apr 09, 2025 |
|
“Austin Chen on Winning, Risk-Taking, and FTX” by Elizabeth
|
Apr 09, 2025 |
|
“Short Timelines don’t Devalue Long Horizon Research” by Vladimir_Nesov
|
Apr 09, 2025 |
|
[Linkpost] “birds and mammals independently evolved intelligence” by bhauth
|
Apr 09, 2025 |
|
“The first AI war will be in your computer” by Viliam
|
Apr 09, 2025 |
|
“Who wants to bet me $25k at 1:7 odds that there won’t be an AI market crash in the next year?” by Remmelt
|
Apr 08, 2025 |
|
“Alignment Faking Revisited: Improved Classifiers and Open Source Extensions” by John Hughes, abhayesian, Akbir Khan, Fabien Roger
|
Apr 08, 2025 |
|
“AI 2027: Responses” by Zvi
|
Apr 08, 2025 |
|
“American College Admissions Doesn’t Need to Be So Competitive” by Arjun Panickssery
|
Apr 08, 2025 |
|
“Most Questionable Details in ‘AI 2027’” by scarcegreengrass
|
Apr 07, 2025 |
|
“AI 2027: Dwarkesh’s Podcast with Daniel Kokotajlo and Scott Alexander” by Zvi
|
Apr 07, 2025 |
|
“How Gay is the Vatican?” by rba
|
Apr 07, 2025 |
|
“The Lizardman and the Black Hat Bobcat” by Screwtape
|
Apr 06, 2025 |
|
“A collection of approaches to confronting doom, and my thoughts on them” by Ruby
|
Apr 06, 2025 |
|
“A Slow Guide to Confronting Doom, v1” by Ruby
|
Apr 06, 2025 |
|
“How much progress actually happens in theoretical physics?” by ChristianKl
|
Apr 06, 2025 |
|
“DeepMind: An Approach to Technical AGI Safety and Security” by Zach Stein-Perlman
|
Apr 06, 2025 |
|
“Among Us: A Sandbox for Agentic Deception” by 7vik, Adrià Garriga-alonso
|
Apr 05, 2025 |
|
“Alignment faking CTFs: Apply to my MATS stream” by joshc
|
Apr 05, 2025 |
|
“Meditation and Reduced Sleep Need” by niplav
|
Apr 05, 2025 |