Currently focused on figuring out how to evaluate and modify the capabilities, values, and goals of AI (especially LLMs) at the ground-truth level and in unsupervised fashion when we cannot apply human judgement to evaluate their output.
You can contact me at firstname.lastname@example.org. Especially contact me if you are interested in these questions, even if you feel like you don’t have a good grasp on them (it’s not clear if anyone has!..).
You can find my twitter here.
May 9, A Two sentence Jailbreak for GPT-4 and Claude & Why Nobody Knows How to Fix It
April 25, AI Alignment Is Turning from Alchemy Into Chemistry
March 8, lifehacks
February 7, My 2022 self (I don't know them) was very wrong about meditation, huge monitors, and... sleep.
January 27, Why AI experts' jobs are always decades from being automated
December 3, Best of Holden Karnofsky and Sam Altman
- Every productivity thought I’ve ever had, as concisely as possible
- Matthew Walker’s “Why We Sleep” Is Riddled with Scientific and Factual Errors
- How Life Sciences Actually Work: Findings of a Year-Long Investigation
- I no longer believe that it’s possible to achieve extremely high productivity sustained over long periods of time working on difficult projects alone, so now I spend the majority of my working time co-working with my friends over video in my virtual gather.town office
- AI Alignment Is Turning from Alchemy Into Chemistry
- A Two sentence Jailbreak for GPT-4 and Claude & Why Nobody Knows How to Fix It
- Forecasting humans becoming generally intelligent with biological anchors: year 10,000,000,000,002,2022
- Planes are still decades away from displacing most bird jobs
- If the moon doesn’t need gravity, why do we? The necessity of understanding for general intelligence
- Why AI experts' jobs are always decades from being automated
- My 2022 self (I don’t know them) was very wrong about meditation, huge monitors, and… sleep.
- Theses on Sleep
- The Effects on Cognition of Sleeping 4 Hours per Night for 12-14 Days: a Pre-Registered Self-Experiment
- Why You Should Start a Blog Right Now
- What Should You Do with Your Life? Directions and Advice
- Why is there only one Elon Musk? Why is there so much low-hanging fruit?
- Reviving Patronage and Revolutionary Industrial Research
- Intelligence killed genius
- What is the alternative to utilitarianism?
- Neurodiversity, mutants, and organisational design
- Every thought about giving and taking advice I’ve ever had, as concisely as possible
- (Autistic) visionaries are not natural-born leaders
- Ideas not mattering is a psyop
- It Is Your Responsibility to Follow Up
- How to make friends over the internet
- Tools / Gear
- My low-demand, worry-free, and healthy diet
- Issues with Bloom et al’s “Are Ideas Getting Harder to Find?” and why total factor productivity should never be used as a measure of innovation
- Research Ideas
- Best of Holden Karnofsky and Sam Altman
- Gwern’s Most Important Writing (in essays, tweets, book reviews, and other forms
- Most Important Slate Star Codex Posts
- Don’t believe self-reported data
- Is anything inherently difficult?
- Why You Should Join Twitter Right Now
- William MacAskill misrepresents the evidence underlying his key arguments in “Doing Good Better”
- Q&A with my high school self: helping 14-16 year old Alexey to deal with his emotions, to ask for help, to talk to people (and his dad), to learn, to get things done.
- On Friendship and on Finding Your People
- 17-20: a Retrospective on Four Years in College
- My journal: years of depression and self-loathing; learning to accept myself and others; overcoming video game addiction
- My Favorite Movies, TV Shows, Books, Podcasts, Music, Video games
- People and Things I Would Fund If I Were a Billionaire
- My 4-monitor computer setup (16-inches + 49-inches + 34-inches + 24-inches
Fiction & Art
- How I got to #1 spot on Hacker News and why you should never try doing the same
- Why You Should Not Go on a Tinder Date with Me
- RAPIDLY PRESS X TO REFUSE TO COME TO TERMS WITH YOUR OWN MORTALITY
- A dying snake
- How Our Commitments Slip Away From Us (pdf, my bachelor’s thesis)
- Why We Likely Underappreciate the Pace of Technological Progress
- Instilling Novel Thought Patterns and Making Your Long-Term Memory Accountable with Anki
- Contra Scott Alexander’s “The Tails Coming Apart as Metaphor for Life”
- Fun Economic Facts
- Interview with Ben Kuhn about productivity, his college experience, job choice, the value of an inside view, the EA community #interview
- Why I switched my newsletters from Substack and Mailchimp to Buttondown
- Polynomial Time Reductions and the P vs NP problem
- Three Questions for Russia
- Online courses and textbooks I recommend
- Where does talent come from? How easy is it to discover talent?
- Tweet rot
- Low tech stuff I recommend
- Can We Trust Peter Turchin?
- Scientific experiments I want to fund
- Tweet-Sized Insight Porn
- Philosophers for Sale
- Julian Jaynes and the Ancient Tablets
- The most we can say about earnings of Substack’s top writers
- Who is the real prophet of longtermism: Will MacAskill or Sam Altman?