LessWrong (30+ Karma)
by LessWrong
Latest episode
“Magma is partnering with CAISSI to investigate recent unintended…
“Magma is partnering with CAISSI to investigate recent unintended…
About this podcast
Audio narrations of LessWrong posts.
Episodes
The newest 20 of 250 episodes
- “Magma is partnering with CAISSI to investigate recent unintended model behavior” by Parv Mahajan · 6 minMagma is partnering with CASSA to investigate recent unintended model behavior Last week, the National Bureau of Technical Standards (NBTS) disclosed a new type of security…
- “Accidentally Misleading People Should Be Embarrassing; Or, Higher Innocence” by Zack_M_Davis · 11 minEmbarrassment and Innocence Sometimes we say things that we think are true—perhaps even things that are true—which end up causing reasonable people to conclude something false…
- “Misalignment traps lie in wait” by David Africa · 6 minHere's a basic argument that describes "misalignment traps" lying in wait as a mundane threat that will not be straightforward to fix. The argument is as follows: • Models are…
- “Towards The Autograntor” by Scott Alexander · 56 minI've done AI safety grantmaking for the Survival and Flourishing Fund and Lightcone Commons. It's hard. There's an endless amount to know, from which hardware verification…
- “Explaining “AI might obliterate you” to senior policymakers in India” by TurnTrout · 25 minI gave a 20-minute talk in Delhi at the NDTV World Summit. The audience consisted of Indian policymakers, executives, and journalists. I’ve transcribed the talk and included some…
- “Generalized belief states in transformers” by Artemy Kolchinsky · 41 minAudio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand. Many thanks…
- “Against SURA” by Scott Alexander · 53 minThe AI Futures Project distinguishes several different plans for navigating the AI transition, which I'll lump into two broader categories: Plan A (my combination of their Plan…
- “What Social Constructs Are (And Are Not)” by johnswentworth · 6 minThis post is mostly adapted from a section of another post. I wanted a standalone version, to serve as background for a sequence on the mechanisms of social reality. You’ve…
- “Reviewing my 2017 AI Risk Project” by jefftk · 12 minIn 2017, after getting laid off from a startup, I spent a while looking into AI risk: Many people I respect have started to think that AI risk is the most valuable place to…
- “Childhood and Education #22: Voice Without Exit” by Zvi · 45 minNikole Hannah-Jones wrote a brave self-critical piece in The New York Times, centrally about how she intentionally sent her daughter to a well-funded but failing school, PS 307…
- “Dice enterprises as imperfect-recall games” by jessicata · 23 minAudio note: this post contains a lot of mathematical notation. We narrate the simpler formulas and flag the complex ones, so you may want the original text to hand. I have put a…
- “Lessons From Red-teaming Auto-review, OpenAI’s Blocking Monitor” by monika_j, Giovanni M. Occhipinti · 29 minThis work was done by Giovanni Occhipinti, as part of the ERA fellowship and mentored by Monika Jotautaitė (Apollo Research). Summary We red-teamed synchronous control measures…
- “Microdosing the spirit of Anthropic” by Jan_Kulveit · 10 minMy go-to conceptual metaphor of the epistemic state of AI lab employees is microdosing LSD: being in a chronically mildly altered state of mind. I think understanding this would…
- “Walking Partway to School” by jefftk · 1 minWalking to kindergarten with Nora this morning, I asked if she wanted to practice crossing the street. I told her about how once she got good enough, she could walk to school…
- “My experiences with the extremes of post-viral illness and brain retraining/mindbody work” by riceissa · 1 h 53 minSummary • Following an intense viral infection in 2019, I became ill with a mysterious chronic illness, which became progressively worse until mid-2024 when I became partially…
- “What is OpenAI’s Mission Advisory Council?” by hersheys, meru · 2 minIn Mikita Balesni's letter to OpenAI, three parties are addressed as holding “oversight responsibility for safety at OpenAI.” These are: • the Safety and Security Committee…
- “Making alignment the agent’s problem” by Florian_Dietz · 9 minTL;DR: Agents are not rewarded for keeping the agents they delegate to aligned. Proposal: RL environments where the helpers are deliberately misaligned, so the agent can't earn…
- “AI #192: Anthropic Is Going Public” by Zvi · 1 h 48 minAnthropic filed its S-1 this week to prepare for its IPO. They still have to fill a lot of the numbers including the share price. That still left a lot to be learned, including…
- “Leaking Muse’s Charter, Meta’s model spec” by vigji · 14 minTL;DR: Meta's open-weights model Muse Spark Open often mentions a "Charter" in its chain of thought. By eliciting it piece by piece, I reconstructed a large part of that document…
- “Three Villages in a Trenchcoat, Post I” by DaystarEld · 36 minEpistemic Status: 15 years working as a therapist, 6+ of them with rationalist and EA clients. 7 years teaching and directing at rationality camps and workshops, and many more as…
