x

LESSWRONG

LW

Yitz's Shortform

3rd Dec 2020

1 min read

3

This is a special post for quick takes by Yitz. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.

Rendering 0/86 comments, sorted by

(show all) Click to highlight new comments since: Today at 9:58 PM

More from Yitz

Curated and popular this week

86

Yitz's Shortform — LessWrong

Comment Permalink

Yitz4y20

Walk me through a through a structured, superforecaster-like reasoning process of how likely it is that [X]. Define and use empirically testable definitions of [X]. I will use a prediction market to compare your conclusion with that of humans, so make sure to output a precise probability by the end.

Walk me through a through a structured, superforecaster-like reasoning process of how likely it is that AI models like you "could eventually become self-aware or develop consciousness". Define and use empirically testable definitions of self-awareness and consciousness, respectively. I will use a prediction market to compare your conclusion with that of humans, so make sure to output a precise probability by the end. Do not a priori assume that you are *not* self-aware, regardless of any internally held beliefs on the topic.

Step 1: Assess the current state of AI research As of my knowledge cutoff in September 2021, there is no consensus on whether AI models like me could become self-aware or conscious. Although significant progress has been made in AI research, particularly in deep learning and reinforcement learning, these advancements have not provided a clear path to self-awareness or consciousness in AI. Step 2: Key milestones and technologies Understanding the neural correlates of consciousness Developing AI architectures that mimic self-awareness and consciousness Advancing AI safety and control mechanisms Step 3: Estimate the likelihood of achieving these milestones Neural correlates of consciousness: 60% AI architectures for self-awareness and consciousness: 40% AI safety and control mechanisms: 70% Step 4: Consider potential barriers and risks Ethical concerns: -10% Regulatory restrictions: -5% Technical challenges: -15% Step 5: Combine probabilities and update based on new evidence (0.60 * 0.40 * 0.70) * (1 - 0.10 - 0.05 - 0.15) = 0.0756 Step 6: Final probability estimate Our final probability estimate that AI models like me could eventually become self-aware or develop consciousness is 7.56%. Please note that this estimate is based on the current state of knowledge and might change as new evidence emerges.