DragonGod

Message

Theoretical Computer Science Msc student at the University of [Redacted] in the United Kingdom.

I'm an aspiring alignment theorist; my research vibes are descriptive formal theories of intelligent systems (and their safety properties) with a bias towards constructive theories.

I think it's important that our theories of...

2498

106

835

DragonGod

"Heretical Thoughts on AI" by Eli Dourado

Abstract Eli Dourado presents the case for scepticism that AI will be economically transformative near term[1]. For a summary and or exploration of implications, skip to "My Take". Introduction > Fool me once. In 1987, Robert Solow quipped, “You can see the computer age everywhere but in the productivity statistics.” Incredibly, this observation happened before the introduction of the commercial Internet and smartphones, and yet it holds to this day. Despite a brief spasm of total factor productivity growth from 1995 to 2005 (arguably due to the economic opening of China, not to digital technology), growth since then has been dismal. In productivity terms, for the United States, the smartphone era has been the most economically stagnant period of the last century. In some European countries, total factor productivity is actually declining. Eli's Thesis In particular, he advances the following sectors as areas AI will fail to revolutionise: * Housing * Most housing challenges are due to land use policy specifically * Housing factors through virtually all sectors of the economy * He points out that the internet did not break up the real estate agent cartel (despite his initial expectations to the contrary) * Energy * Regulatory hurdles to deployment * There are AI optimisation opportunities elsewhere in the energy pipeline, but the regulatory hurdles could bottleneck the economic productivity gains * Transportation * The issues with US transportation infrastructure have little to do with technology and are more regulatory in nature * As for energy, there are optimisation opportunities for digital tools, but the non-digital issues will be the bottleneck * Health * > The biggest gain from AI in medicine would be if it could help us get drugs to market at lower cost. The cost of clinical trials is out of control—up from $10,000 per patient to $500,000

146Jan 19, 2023

Why The Focus on Expected Utility Maximisers?

118Dec 27, 2022

Sparks of Artificial General Intelligence: Early experiments with GPT-4 | Microsoft Research

68Mar 23, 2023

Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind

62Jan 13, 2023

DragonGod

Message

2498

106

835

Change My Mind: Thirders in "Sleeping Beauty" are Just Doing Epistemology Wrong

Preamble > Sleeping Beauty volunteers to undergo the following experiment and is told all of the following details: On Sunday she will be put to sleep. Once or twice, during the experiment, Sleeping Beauty will be awakened, interviewed, and put back to sleep with an amnesia-inducing drug that makes her...

Oct 16, 20248

Consequentialism is in the Stars not Ourselves

Polished from my shortform. Epistemic Status Thinking out loud. Introduction I've argued that system wide/total optimisation for an objective function in the real world is so computationally intractable as to be prohibited by the laws of physics of our universe[1]. Yet it's clearly the case that e.g., evolution is optimising...

Apr 24, 20237

Is "Strong Coherence" Anti-Natural?

Related: * Contra "Strong Coherence" * why assume AGIs will optimize for fixed goals * Why The Focus on Expected Utility Maximisers? Background and Core Concepts I operationalised "strong coherence" as: > Informally: a system has immutable terminal goals. > > Semi-formally: a system's decision making is well described as...

Apr 11, 202323

Feature Request: Right Click to Copy LaTeX

Something I do frequently is run into a block of LaTeX that I'm not sure I fully grasp. At such a point, what I'd like to do is just copy the equation and paste it to GPT-4 and have it explain it to me step by step, then iterate on...

Apr 8, 202318

Beren's "Deconfusing Direct vs Amortised Optimisation"

Preamble I heavily recommend @beren's "Deconfusing Direct vs Amortised Optimisation". It's a very important conceptual clarification that has changed how I think about many issues bearing on technical AI safety. Currently, it's the most important blog post I've read this year. This sequence (if I get around to completing it)...

Apr 7, 202352

Is "Recursive Self-Improvement" Relevant in the Deep Learning Paradigm?

Disclaimer I wrote this three months ago, and abandoned it[1]. I currently do not plan to return to it anytime soon, but I have nonetheless found myself wanting of a document I could point to for why I'm not particularly enthused by or overly concerned with "recursive self improvement". As...

Apr 6, 202332

Orthogonality is Expensive

@beren discusses the assumption that intelligent systems would be well factored into a world model, objectives/values and a planning system. He highlights that this factorisation doesn't describe intelligent agents created by ML systems (e.g. model free RL) well. Model free RL agents don't have cleanly factored architectures but tend to...

Apr 3, 202321

Load More (7/101)

LESSWRONG
LW

LESSWRONG
LW

DragonGod

DragonGod

DragonGod

"Heretical Thoughts on AI" by Eli Dourado

Why The Focus on Expected Utility Maximisers?

Sparks of Artificial General Intelligence: Early experiments with GPT-4 | Microsoft Research

Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind

DragonGod

Change My Mind: Thirders in "Sleeping Beauty" are Just Doing Epistemology Wrong

Consequentialism is in the Stars not Ourselves

Is "Strong Coherence" Anti-Natural?

Feature Request: Right Click to Copy LaTeX

Beren's "Deconfusing Direct vs Amortised Optimisation"

Is "Recursive Self-Improvement" Relevant in the Deep Learning Paradigm?

Orthogonality is Expensive

"Heretical Thoughts on AI" by Eli Dourado

Why The Focus on Expected Utility Maximisers?

Sparks of Artificial General Intelligence: Early experiments with GPT-4 | Microsoft Research

Tracr: Compiled Transformers as a Laboratory for Interpretability | DeepMind

Change My Mind: Thirders in "Sleeping Beauty" are Just Doing Epistemology Wrong

Consequentialism is in the Stars not Ourselves

Is "Strong Coherence" Anti-Natural?

Feature Request: Right Click to Copy LaTeX

Beren's "Deconfusing Direct vs Amortised Optimisation"

Is "Recursive Self-Improvement" Relevant in the Deep Learning Paradigm?

Orthogonality is Expensive