hackertube.io

Intelligence and Stupidity: The Orthogonality Thesis

Robert Miles AI Safety · explainer · Watch on YouTube

AI safety, AGI & impact

What it is

Robert Miles explains the orthogonality thesis: how an agent can be highly intelligent while pursuing goals that seem stupid or alien to humans. He separates intelligence from goals and touches on the stamp-collector example.

Why Hacker News recommends it

HN people use it as the standard short explanation for why AI can understand human ethics without sharing them, and often recommend the whole channel.

  • 6 people recommended it
  • 6 different months
  • 3 strong recommendations
  • first 2022, last 2026

What HN commenters said

  1. “this video to me states the problem in a nutshell (that whole channel is gold)”

    States the problem in a nutshell

    pegasus, 2023-03 · Strong recommendation · in “Show HN: GPT-4 Reverse Turing Test”

  2. “I highly recommend Rob Miles channel on YouTube.”

    Shows how hard it is to give trained AI the goals we want.

    simonh, 2023-05 · Strong recommendation · in “OpenAI chief goes before US Congress to propose licenses for building AI”

  3. “It may also be worthwhile checking out the Rob Miles video on the Orthogonality Thesis”

    Worth checking out on the Orthogonality Thesis

    casebash, 2022-12 · Recommendation · in “Show HN: Help, I let GPTChat control my computer”

  4. “This is a good video explaining that”

    Explains why an AI can understand human ethics without following them.

    circuit10, 2023-03 · Recommendation · in “Pausing AI Developments Isn't Enough. We Need to Shut It All Down”

  5. “there are great learning materials available, including a well-made youtube series by Robert Miles.”

    Part of a well-made series on orthogonality and instrumental convergence.

    mitthrowaway2, 2023-04 · Recommendation · in “BabyAGI: An Autonomous and Self-Improving Agent”

  6. “Rob miles has some really good videos on AI safety research which touches on how AGI would think.”

    Rob Miles' videos explain how AGI would think and pursue goals.

    AstroBen, 2025-04 · Recommendation · in “AGI Is Still 30 Years Away – Ege Erdil and Tamay Besiroglu”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: orthogonality thesis, ai safety, agi, goals vs intelligence, robert miles

Also recommended by the same people