Marcos Feed
Tuesday, August 5, 2025
Fresh Fruit Tourism
Published on August 5, 2025 2:31 AM GMTAs incomes have risen, it's important for Americans to find new ways to spend ever-increasing amounts of money. I propose that we spend...
Do LLMs have a conscience? Investigating model ethics under pressure
Published on August 5, 2025 12:32 AM GMTThis work was done by me and Joshua Lum over roughly 1 week as part of the first run of RECAP, a Singapore-based...
“Momentism”: Ethics for Boltzmann Brains
Published on August 5, 2025 2:09 AM GMTIf[1] you’re a Boltzmann brain, you should probably just enjoy the moment.This is probably true not just from an obvious standpoint, but from...
Human Augmentation Summit at MIT Media Lab | August 23 | Augmentation Lab
Published on August 5, 2025 1:43 AM GMTThe LessWrong community is invited to join us on August 23, 2025, at the MIT Media Lab for a full-day summit exploring the...
Pro AI Bots Scraping List Archives
Published on August 5, 2025 1:20 AM GMT I'm on various mailing lists, and the archives are a trove of niche knowledge. A dance calling list I'm on is considering...
AI Optimization, not Options or Optimism
Published on August 5, 2025 1:07 AM GMTThis post is a response to Eric Drexler's recent article, "AI Options, not ‘Optimism‘", and his ideas as I understand them in general.Control...
You Are Moving Out Of Your Reference Class
Published on August 5, 2025 12:20 AM GMTThe idea to write this article emerged from some of my discussions with fellow rationalists, transhumanists, and AI safety researchers about what to...
Steering LLM Agents: Temperaments or Personalities?
Published on August 5, 2025 12:40 AM GMTAuthor: Skylar DeTureReading time: ~8-10 minutesEpistemic status: Speculative framework building on established psychology research and recent Anthropic findingsAbstract: I propose a three-layer framework...
Towards Alignment Auditing as a Numbers-Go-Up Science
Published on August 4, 2025 10:30 PM GMTThanks to Rowan Wang and Buck Shlegeris for feedback on a draft.What is the job of an alignment auditing researcher? In this post,...
It turns out that DNNs are remarkably interpretable.
Published on August 4, 2025 10:18 PM GMTI recently posted a paper suggesting that deep networks may harbor an implicitly linear model, recoverable via a form of gradient denoising. The...
Monday, August 4, 2025
Dissolving moral philosophy: from pain to meta-ethics
Published on August 4, 2025 8:20 PM GMTThis is an extract from an appendix of one of my longer blog posts that I keep referring to. What is pain? Why...
Navigating Security: Fighting flammability with fire (when safe)
Published on August 4, 2025 7:58 PM GMTSo insecurity is the driver of both irrationality and psychological "stuckness". It's why we can't "just look at reality" and instead get ourselves...
ACX Atlanta August Meetup
Published on August 4, 2025 7:52 PM GMTThe August 2025 Meetup will be August 16th at Bold Monk at 2:00 PMWe return to Bold Monk brewing for a vigorous discussion...
Ode to the EarPods
Why I’m making room for EarPods in a world ruled by AirPods.
Permanent Disempowerment is the Baseline
Published on August 4, 2025 5:43 PM GMTPermanent disempowerment without restrictions on quality of life achievable with relatively meager resources (and no extinction) seems to be a likely outcome for...
If you can generate obfuscated chain-of-thought, can you monitor it?
Published on August 4, 2025 3:46 PM GMTtldr:Chain-of-thought (CoT) monitoring is a proposed safety mechanism for overseeing AI systems, but its effectiveness against deliberately obfuscated reasoning remains unproven. "Obfuscated" reasoning...
On Altman’s Interview With Theo Von
Published on August 4, 2025 3:10 PM GMTSam Altman talked recently to Theo Von. Double click to interact with video Theo is genuinely engaging and curious throughout. This made me...
Among many things my brain comes up (and barely ever finishes) - #rust frontend for Dosbox(X) becaus
Among many things my brain comes up (and barely ever finishes) - #rust frontend for Dosbox(X) because I'm too stupid to configure RetroArch, Launchbox is boring and I miss D-Fend...
Should we aim for flourishing over mere survival? The Better Futures series.
Published on August 4, 2025 2:28 PM GMTToday, Forethought and I are releasing an essay series called Better Futures, here.[1] It’s been something like eight years in the making, so...
Framework I made for general "productivity"
Published on August 4, 2025 8:40 AM GMTHi, wrote down some thoughts on a generalized framework to think about how to get work done. In spirit of taking my own...
Welcome to Postreads
Follow your favorite sources, create custom feeds, and discover quality content from across the web. Use as your personal front page or private reading space.
Start Your FeedFollowing
5 sources
