Podcast Episodes
Back to Search“Unless its governance changes, Anthropic is untrustworthy” by null
Anthropic is untrustworthy.
This post provides arguments, asks questions, and documents some examples of Anthropic's leadership being misleading and…
7 months, 3 weeks ago
“Alignment remains a hard, unsolved problem” by null
Thanks to (in alphabetical order) Joshua Batson, Roger Grosse, Jeremy Hadfield, Jared Kaplan, Jan Leike, Jack Lindsey, Monte MacDiarmid, Francesco M…
7 months, 3 weeks ago
“Video games are philosophy’s playground” by Rachel Shu
Crypto people have this saying: "cryptocurrencies are macroeconomics' playground." The idea is that blockchains let you cheaply spin up toy economie…
7 months, 4 weeks ago
“Stop Applying And Get To Work” by plex
TL;DR: Figure out what needs doing and do it, don't wait on approval from fellowships or jobs.
If you...
Have short timelines Have been struggling …
8 months ago
“Gemini 3 is Evaluation-Paranoid and Contaminated” by null
TL;DR: Gemini 3 frequently thinks it is in an evaluation when it is not, assuming that all of its reality is fabricated. It can also reliably outpu…
8 months ago
“Natural emergent misalignment from reward hacking in production RL” by evhub, Monte M, Benjamin Wright, Jonathan Uesato
Abstract
We show that when large language models learn to reward hack on production RL environments, this can result in egregious emergent misalignm…
8 months ago
“Anthropic is (probably) not meeting its RSP security commitments” by habryka
TLDR: An AI company's model weight security is at most as good as its compute providers' security. Anthropic has committed (with a bit of ambiguity,…
8 months ago
“Varieties Of Doom” by jdp
There has been a lot of talk about "p(doom)"over the last few years. This has always rubbed me the wrong waybecause "p(doom)" didn't feel like it ma…
8 months ago
“How Colds Spread” by RobertM
It seems like a catastrophic civilizational failure that we don't have confident common knowledge of how colds spread. There have been a number of s…
8 months ago
“New Report: An International Agreement to Prevent the Premature Creation of Artificial Superintelligence” by Aaron_Scher, David Abecassis, Brian Abeyta, peterbarnett
TLDR: We at the MIRI Technical Governance Team have released a report describing an example international agreement to halt the advancement towards …
8 months ago