Podcast Episodes
Back to Search"Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models" by Anders Cairns Woodruff, Francis Rhys Ward, Dewi Gould, Rauno Arike, Jason R Brown, Jo Jiao, wlanderson, ariana_azarbal, harrymayne, Patrick Leask
(see full author list at the end)
PAPER LINK
About a year ago, METR showed that the length of tasks frontier models can reliably complete doubles ev…
1 month, 1 week ago
"Even “illegible” Mythos reasoning traces seem pretty legible" by faul_sname
The Claude Fable 5/Mythos 5 System Card has a section in which they talk about illegible reasoning, and provide an "extreme" example thereof.
Models…
1 month, 1 week ago
"Sequent: scale and automation for higher confidence in alignment" by Geoffrey Irving, Alex HT, Jesse Hoogland, Daniel Murfet, Jacob Pfau, Marco Cozzi, Stan van Wingerden
Alignment is not on track
Artificial superintelligence (ASI) may be developed in the next few years. It is unclear whether alignment is on track to …
1 month, 1 week ago
"The Machines Lack Honour" by Raymond Douglas
The battle lines of the AI morality debate are being laid down. On one side you have the ChatGPT dogma: AI as mere tools with no real preferences or…
1 month, 1 week ago
"My favorite depiction of utopia" by Caleb Biddulph
For those who are trying to bring about a glorious transhuman utopia with the help of hopefully-aligned ASI, I think it's worth thinking explicitly …
1 month, 2 weeks ago
"Announcing the ARC White-Box Estimation Challenge" by Jacob_Hilton
ARC has teamed up with AIcrowd to launch the ARC White-Box Estimation Challenge, a contest to improve upon our estimation algorithms for random MLPs…
1 month, 2 weeks ago
"Lighthaven East - A Feasibility Study" by JohnofCharleston
As a bureaucrat, my role is to annoy my friends. Someone voices an idea, “Wouldn’t it be nice if…” or “I wonder if we could…” I make a note. I do so…
1 month, 3 weeks ago
"Empowerment, corrigibility, etc. are simple abstractions (of a messed-up ontology)" by Steven Byrnes
1.1 Tl;dr
Alignment is often conceptualized as AIs helping humans achieve their goals: AIs that increase people's agency and empowerment; AIs that a…
1 month, 3 weeks ago
"Trees are mostly made of air and a generalizable lesson for AI safety" by zroe1
At the risk of embarrassing myself, I’ll share a confession.
For context, I took five years of Latin: four in high school and one in college. In add…
1 month, 3 weeks ago
"Mnemonic portraits for 19,023 human genes" by Brinedew
Back in 2013, Scott Alexander wrote in Extreme mnemonics:
JS-154 is one of five metabolic products of netamine; however, the enzyme that produces it…
1 month, 3 weeks ago