hackertube.io

Why Asimov's Laws of Robotics Don't Work - Computerphile

Computerphile · explainer · Watch on YouTube

AI safety, AGI & impactRobotics

What it is

Rob Miles explains for Computerphile why simple rule sets like Asimov's Three Laws cannot make robots and AI safe. Terms like harm and human are too ambiguous to specify precisely.

Why Hacker News recommends it

Pointed to in AI safety debates as a short explanation of why encoding human values as simple rules is so hard.

  • 2 people recommended it
  • 2 different months
  • 0 strong recommendations
  • first 2015, last 2023

What HN commenters said

  1. “interesting thoughts on the subject from Computerphile”

    Why Asimov's laws fail as a rule set for robots.

    bauc, 2015-12 · Recommendation · in “new TLD: .BOT”

  2. “I found this video insightful on the matter from Computerphile”

    Argues AI following such laws is impossible given ambiguous terms.

    ornornor, 2023-03 · Recommendation · in “Ask HN: How are you using GPT to be productive?”

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

Topics: asimov's laws, ai alignment, rob miles, robot ethics, value specification

Also recommended by the same people