Jonkman Microblog
  • Login
Show Navigation
  • Public

    • Public
    • Network
    • Groups
    • Popular
    • People

Conversation

Notices

  1. sungo (sungo@hackers.town)'s status on Monday, 15-Apr-2019 16:42:31 EDT sungo sungo

    "The human's decisions were based on an unbroken straight line chain of 85 million years of "I am the primate who did not get eaten", layered with decades of fine motor control trailing. Whereas the AI based its decisions on whatever ad hoc junk a bunch of low-paid contractors dumped into the training set over a period maybe as long as 18 months.

    So they're building an AI whose goal is to lie to you -- to build your confidence in decisions made by AIs.

    We are so completely doomed."

    - JWZ - "Frogger AI Explains Its Decisions" https://www.jwz.org/blog/2019/04/frogger-ai-explains-its-decisions/

    In conversation Monday, 15-Apr-2019 16:42:31 EDT from hackers.town permalink

    Attachments

    1. Frogger AI Explains Its Decisions
      ...using automated, plausible lies: After training the AI system to play the popular arcade game Frogger, and documenting how human players explained the decisions they made while playing the game, the team of researchers developed the agent to generate language in real time to explain the motivations behind its actions. [...] When it comes to neural networks -- a kind of AI architecture made
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

Jonkman Microblog is a social network, courtesy of SOBAC Microcomputer Services. It runs on GNU social, version 1.2.0-beta5, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All Jonkman Microblog content and data are available under the Creative Commons Attribution 3.0 license.

Switch to desktop site layout.