Podcast Episodes
Back to Search“The Most Common Bad Argument In These Parts” by J Bostock
I've noticed an antipattern. It's definitely on the dark pareto-frontier of "bad argument" and "I see it all the time amongst smart people". I'm con…
11 months, 2 weeks ago
“Towards a Typology of Strange LLM Chains-of-Thought” by 1a3orn
Intro
LLMs being trained with RLVR (Reinforcement Learning from Verifiable Rewards) start off with a 'chain-of-thought' (CoT) in whatever language t…
11 months, 2 weeks ago
“I take antidepressants. You’re welcome” by Elizabeth
It's amazing how much smarter everyone else gets when I take antidepressants.
It makes sense that the drugs work on other people, because there's …
11 months, 2 weeks ago
“Inoculation prompting: Instructing models to misbehave at train-time can improve run-time behavior” by Sam Marks
This is a link post for two papers that came out today:
Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test…
11 months, 2 weeks ago
“Hospitalization: A Review” by Logan Riggs
I woke up Friday morning w/ a very sore left shoulder. I tried stretching it, but my left chest hurt too. Isn't pain on one side a sign of a heart a…
11 months, 2 weeks ago
“What, if not agency?” by abramdemski
Sahil has been up to things. Unfortunately, I've seen people put effort into trying to understand and still bounce off. I recently talked to someone…
11 months, 2 weeks ago
“The Origami Men” by Tomás B.
Of course, you must understand, I couldn't be bothered to act. I know weepers still pretend to try, but I wasn't a weeper, at least not then. It isn…
11 months, 3 weeks ago
“A non-review of ‘If Anyone Builds It, Everyone Dies’” by boazbarak
I was hoping to write a full review of "If Anyone Builds It, Everyone Dies" (IABIED Yudkowski and Soares) but realized I won't have time to do it. S…
11 months, 3 weeks ago
“Notes on fatalities from AI takeover” by ryan_greenblatt
Suppose misaligned AIs take over. What fraction of people will die? I'll discuss my thoughts on this question and my basic framework for thinking ab…
11 months, 3 weeks ago
“Nice-ish, smooth takeoff (with imperfect safeguards) probably kills most ‘classic humans’ in a few decades.” by Raemon
I wrote my recent Accelerando post to mostly stand on it's own as a takeoff scenario. But, the reason it's on my mind is that, if I imagine being ve…
11 months, 3 weeks ago