AI ALIGNMENT FORUM
Tags
AF

Recursive Self-Improvement

•

Applied to 0 Motivation Mapping through Information Theory by Gabriel de Siqueira Brito 9d ago

•

Applied to 1 What If We Rebuild Motivation with the Fermi ESTIMATion? by Gabriel de Siqueira Brito 16d ago

•

Applied to o1: A Technical Primer by Jesse Hoogland 17d ago

•

Applied to 2 What if Life Comes with a Natural Calibration to Estimate you? by Gabriel de Siqueira Brito 18d ago

•

Applied to 3 What If We Could Map Our Motivation as Channels of Flow? by Gabriel de Siqueira Brito 18d ago

•

Applied to notes on prioritizing tasks & cognition-threads by Emrik 1mo ago

•

Applied to Why Recursive Self-Improvement Might Not Be the Existential Risk We Fear by Nassim_A 1mo ago

•

Applied to What program structures enable efficient induction? by Daniel C 4mo ago

•

Applied to AGI will be made of heterogeneous components, Transformer and Selective SSM blocks will be among them by Roman Leventov 1y ago

•

Applied to LLMs May Find It Hard to FOOM by Roger Dearnaley 1y ago

•

Applied to Eric Schmidt on recursive self-improvement by Nikola Jurkovic 1y ago

•

Applied to The AI Explosion Might Never Happen by Steve Newman 1y ago

•

Applied to A Simple Theory Of Consciousness by SherlockHolmes 1y ago

•

Applied to ACI#4: Seed AI is the new Perpetual Motion Machine by Akira Pyinya 1y ago

•

Applied to Contra Anton 🏴‍☠️ on Kolmogorov complexity and recursive self improvement by Raymond Arnold 1y ago

•

Applied to Do not miss the cutoff for immortality! There is a probability that you will live forever as an immortal superintelligent being and you can increase your odds by convincing others to make achieving the technological singularity as quickly and safely as possible the collective goal/project of all of humanity, Similar to "Fable of the Dragon-Tyrant." by Oliver--Klozoff 1y ago

•

Applied to "textbooks are all you need" by bhauth 2y ago

•

Applied to human intelligence may be alignment-limited by bhauth 2y ago

•

Applied to Proposal: labs should precommit to pausing if an AI argues for itself to be improved by NickGabs 2y ago