jacob_cannell

Brain Efficiency: Much More than You Wanted to Know

What if the brain is highly efficient? To be more specific, there are several interconnected key measures of efficiency for physical learning machines: * energy efficiency in ops/J * spatial efficiency in ops/mm^2 or ops/mm^3 * speed efficiency in time/delay for key learned tasks * circuit/compute efficiency in size and steps for key low level algorithmic tasks [1] * learning/data efficiency in samples/observations/bits required to achieve a level of circuit efficiency, or per unit thereof * software efficiency in suitability of learned algorithms to important tasks, is not directly addressed in this article[2] Why should we care? Brain efficiency matters a great deal for AGI timelines and takeoff speeds, as AGI is implicitly/explicitly defined in terms of brain parity. If the brain is about 6 OOM away from the practical physical limits of energy efficiency, then roughly speaking we should expect about 6 OOM of further Moore's Law hardware improvement past the point of brain parity: perhaps two decades of progress at current rates, which could be compressed into a much shorter time period by an intelligence explosion - a hard takeoff. But if the brain is already near said practical physical limits, then merely achieving brain parity in AGI at all will already require using up most of the optimizational slack, leaving not much left for a hard takeoff - thus a slower takeoff. In worlds where brains are efficient, AGI is first feasible only near the end of Moore's Law (for non-exotic, irreversible computers), whereas in worlds where brains are highly inefficient, AGI's arrival is more decorrelated, but would probably come well before any Moore's Law slowdown. In worlds where brains are ultra-efficient, AGI necessarily becomes neuromorphic or brain-like, as brains are then simply what economically efficient intelligence looks like in practice, as constrained by physics. This has important implications for AI-safety: it predicts/postdicts the success of AI app

210Jan 6, 2022

jacob_cannell

Message

I have a compute-market startup called vast.ai, and I'm working towards aligned AI. Currently seeking networking, collaborators, and hires - especially top notch cuda/gpu programmers.

My personal blog: https://entersingularity.wordpress.com/

6216

1957

16y

Are humans misaligned with evolution?

There is an argument that although humans evolved under pressure to maximize inclusive genetic fitness (IGF), humans don't actually try to maximize their own IGF. This, as the argument goes, shows that in the one case we have of a process creating general intelligence, it was not the case that...

Oct 19, 202342

Evolution Solved Alignment (what sharp left turn?)

Some people like to use the evolution of homo sapiens as an argument by analogy concerning the apparent difficulty of aligning powerful optimization processes: > And in the same stroke that its capabilities leap forward, its alignment properties are revealed to be shallow, and to fail to generalize. The much...

Oct 12, 202329

Contra Yudkowsky on Doom from Foom #2

This is a follow up and partial rewrite to/of an earlier part #1 post critiquing EY's specific argument for doom from AI go foom, and a partial clarifying response to DaemonicSigil's reply on efficiency. AI go Foom? By Foom I refer to the specific idea/model (as popularized by EY, MIRI,...

Apr 27, 202394

Contra Yudkowsky on AI Doom

Eliezer Yudkowsky predicts doom from AI: that humanity faces likely extinction in the near future (years or decades) from a rogue unaligned superintelligent AI system. Moreover he predicts that this is the default outcome, and AI alignment is so incredibly difficult that even he failed to solve it. EY is...

Apr 24, 202391

Empowerment is (almost) All We Need

Intro What/who would you like to become in a thousand subjective years? or a million? Perhaps, like me, you wish to become posthuman: to transcend mortality and biology, to become a substrate independent mind, to wear new bodies like clothes, to grow more intelligent, wise, wealthy, and connected, to explore...

Oct 23, 202261

AI Timelines via Cumulative Optimization Power: Less Long, More Short

TLDR: We can best predict the future by using simple models which best postdict the past (ala Bayes/Solomonoff). A simple model based on net training compute postdicts the relative performance of successful biological and artificial neural networks. Extrapolation of this model into the future leads to short AI timelines: ~75%...

Oct 6, 2022138

LOVE in a simbox is all you need

Learning Other's Values or Empowerment in simulation sandboxes is all you need TL;DR: We can develop self-aligning DL based AGI by improving on the brain's dynamic alignment mechanisms (empathy/altruism/love) via safe test iteration in simulation sandboxes. AGI is on track to arrive soon[1] through the same pragmatic, empirical and brain...

Sep 28, 202267

Load More (7/28)

LESSWRONG
LW

LESSWRONG
LW

jacob_cannell

jacob_cannell

jacob_cannell

Brain Efficiency: Much More than You Wanted to Know

The Brain as a Universal Learning Machine

AI Timelines via Cumulative Optimization Power: Less Long, More Short

Contra Yudkowsky on Doom from Foom #2

jacob_cannell

Are humans misaligned with evolution?

Evolution Solved Alignment (what sharp left turn?)

Contra Yudkowsky on Doom from Foom #2

Contra Yudkowsky on AI Doom

Empowerment is (almost) All We Need

AI Timelines via Cumulative Optimization Power: Less Long, More Short

LOVE in a simbox is all you need

Brain Efficiency: Much More than You Wanted to Know

The Brain as a Universal Learning Machine

AI Timelines via Cumulative Optimization Power: Less Long, More Short

Contra Yudkowsky on Doom from Foom #2

Are humans misaligned with evolution?

Evolution Solved Alignment (what sharp left turn?)

Contra Yudkowsky on Doom from Foom #2

Contra Yudkowsky on AI Doom

Empowerment is (almost) All We Need

AI Timelines via Cumulative Optimization Power: Less Long, More Short

LOVE in a simbox is all you need