Artificially Intelligent

Any mimicry distinguishable from the original is insufficiently advanced.

  • Fractional progress estimates for AI timelines and implied resource requirements

    | 2150 words

    Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. This post was written by Mark Xu based on interviews with Carl Shulman. It was paid for by Open Philanthropy but is not representative of their views. A draft was sent to Robin Hanson for review but...

  • Intermittent Distillations #4

    | 2949 words

    The Semiconductor Supply Chain: Assessing National Competitiveness (Saif M. Khan, Alexander Mann, Dahlia Peterson) The Semiconductor Supply Chain: Assessing National Competitiveness Summary This report analyzes the current supply chain for semiconductors. It particularly focuses on which portions of the supply chain are controlled by US and its allies and China....

  • Anthropic Effects in Estimating Evolution Difficulty

    | 1055 words

    Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Thanks to Linchuan Zhang, Mauricio Baker, Jack Ryan and Carl Shulman for helpful comments and suggestions. Remaining mistakes are my own. Epistemic status: “There is something fascinating about [anthropics]. One gets such wholesale returns of conjecture out...

  • A Rough Perspective on Strategy Stealing

    | 2394 words

    Related to The strategy-stealing assumption. Introduction Imagine there’s something called power, which refers to roughly flexible influence over the future. Humanity currently has 100% of the power. People are concerned that AI systems pose an existential risk; this concern is equivalent to worrying that at some point in the future,...

  • The Wild World of Policy Debate

    | 5062 words

    This is a transcript of a talk I gave to my house. It was transcribed by otter.ai and edited by Sabrina Chwalek. Today, I will tell you about the wild world of policy debate, which I inhabited for approximately four years when I was in high school. Some notes, I...

  • Rogue AGI Embodies Valuable Intellectual Property

    | 1082 words

    Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. This post was written by Mark Xu based on interviews with Carl Shulman. It was paid for by Open Philanthropy but is not representative of their views. Summary: Rogue AGI has access to its embodied IP. This...

  • An Intuitive Guide to Garrabrant Induction

    | 7388 words

    Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. This post is a high-level summary of the core insights and arguments in Logical Induction, a MIRI paper from 2016. It’s intended for people without much mathematical training. Numbers in [brackets] indicate the section of the paper...

  • Intermittent Distillations #3

    | 3406 words

    Mundane solutions to exotic problems (Paul Christiano) Mundane solutions to exotic problems Summary Thinking about AI safety often leads to considering exotic problems: models purposefully altering their gradients, agents hiding their capabilities to defect when an opportunity arises, or humans being vulnerable to side-channel attacks. These exotic problems might seem...

  • Lumenator Recipe

    | 109 words

    Let there be light. My current lumenator consists of three copies of the following: 2x LED Pure White CRI 95 Corn Bulb 1x LED Warm White CRI 95 Corn Bulb 1x Adesso Floor Lamp My previous lumenator consisted of: 3x 16 bulb light string 32x 5000k CRI 90 LED 16x...

  • Pre-Training + Fine-Tuning Favors Deception

    | 962 words

    Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Thanks to Evan Hubinger for helpful comments and discussion. Currently, to obtain models useful for some task X, models are pre-trained on some task Y, then fine-tuned on task X. For example, to obtain a model that...