Podcast Episodes
Back to Search“Product Alignment is not Superintelligence Alignment (and we need the latter to survive)” by plex
tl;dr: progress on making Claude friendly[1] is not the same as progress on making it safe to build godlike superintelligence. solving the former do…
3 weeks, 1 day ago
“Co-Found Lens Academy With Me. (We have early users and funding)” by Luc Brinkman
tl;dr. Lens Academy is creating scalable superingelligence x-risk education with several USPs. Current team: Luc (full time founder, technical gener…
3 weeks, 1 day ago
“Slack in Cells, Slack in Brains” by Mateusz Bagiński
[A veridically metaphorical explanation of why you shouldn't naïvely cram your life with local optimizations (even for noble or altruistic reasons).…
3 weeks, 1 day ago
“I am definitely missing the pre-AI writing era” by N. Cailie
Yesterday, I wrote my first technical draft on what I was working on with the goal to share it publicly on here (well using an account dedicated to …
3 weeks, 1 day ago
“The state of AI safety in four fake graphs” by Boaz Barak
Here is a quick overview of my intuitions on where we are with AI safety in early 2026:
3 weeks, 1 day ago
“AI should be a good citizen, not just a good assistant” by Tom Davidson, wdmacaskill
Introduction
Consider a lorry driver who sees a car crash and pulls over to help, even though it’ll delay his journey. Or a delivery driver who noti…
3 weeks, 2 days ago
″(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL” by 7vik, Sid Black, Joseph Bloom
Authors: Satvik Golechha*, Sid Black*, Joseph Bloom
* Equal Contribution.
This work was done as part of the Model Transparency team at the UK AI Sec…
3 weeks, 2 days ago
[Linkpost] “Parkinson’s Law of Worry” by Jakub Halmeš
This is a link post.
Parkinson's law says that "Work expands so as to fill the time available for its completion." I think that a similar observation…
3 weeks, 2 days ago
“Folie à Machine: LLMs and Epistemic Capture” by DaystarEld
"Truly, whoever can make you believe absurdities can make you commit atrocities." — Voltaire, 1765
A man in his late forties discovers a new passion…
3 weeks, 3 days ago
“Stop asking “how good is this” to decide between donation opportunities I recommend” by Zach Stein-Perlman
Prospective donors often ask how cost-effective my team's various recommendations are — they want to donate to the most cost-effective opportunity. …
3 weeks, 3 days ago