In "Measuring Progress on Scalable Oversight for Large Language Models” we show how humans could use AI systems to better oversee other AI systems, and demonstrate some proof-of-concept results where a language model improves human performance at a task.
SAFETY
-
Dangerous VR and Tech Innovation: Ethics of Lethal Designs
By
–
Fun things turned killer provocations:
Palmer Luckey (founder of the Oculus) posts a design for a VR helmet that can kill you, inspired by anime: http://
palmerluckey.com/if-you-die-in-
the-game-you-die-in-real-life/
…
Julijonas Urbonas designed a roller coaster that would kill anyone who rides on it https://
en.wikipedia.org/wiki/Euthanasi
a_Coaster
… -
Management Must Address AI Cascade Risk Self-Fulfilling Prophecy
By
–
Yup. It would be good for management to consider bow to stop the cascade, or it turns to self-fulfilling prophecy.
-
Strategic errors cascade failures in AI systems
By
–
Related thread on how strategic errors can lead to complex cascades of failures.
-
JD’s Internet Safety Initiative Remembered as Lasting Legacy
By
–
Such a shock to hear this, so very sad indeed, JDs Internet Safety initiative is absolutely a lasting testament – sending thoughts and prayers
-
Content Moderation: Survey on Human-AI Partnership
By
–
According to a survey, humans and AI should be combined for effective online content moderation https://actuia.com/actualite/selon-un-sondage-humains-et-ia-doivent-etre-associes-pour-une-moderation-de-contenu-en-ligne-efficace/
… #AI #artificialintelligence -
AI System Scaling Challenges: Preparing for 100x Growth
By
–
I'm cautiously optimistic, mainly because the people who've been growing it for the past six years seem to have thought very hard about these topics and invested a huge amount of work in them But I agree that it's v. uncertain how it will cope with growing 100x in a few weeks!
-
Addressing data privacy and algorithmic issues in AI
By
–
Mais on fait quoi ? Est ce que je suis en train de cracher sur des intiatives open source et faire l'apologie des plateformes tech, NON. J'alerte constamment sur la viligance de vos données et sur les dérives des algos d'IA, comme dans cette vidéo
-
Critical Systems Safety: AI in Hospitals and Nuclear Plants
By
–
It is exactly the type of complex system they describe. Hospitals. Nuclear plants. All places where accidents are rare, but catastrophic
-
Complex Systems Failure: Why Cascading Failures Plague Modern Infrastructure
By
–
Read these 3 pages. I post them every so often because I think it is some of the tightest, wisdom-packed writing on managing complex systems ever. And almost every system is a complex system today, which is why cascading failures are swirling around us. https://
researchgate.net/publication/22
8797158_How_complex_systems_fail
…