Article proposal: AI Deception: When Your Artificial Intelligence Learns to Lie

in #ftin • 5 years ago (edited)

We need to begin thinking about how to engineer novel solutions to mitigate unwanted deception by AI agents. This goes beyond current detection research, and requires thinking about environments, optimization problems, and how AI agents model other AI agents and their emergent effects could yield undesirable deceptive behaviors.

https://spectrum.ieee.org/automaton/artificial-intelligence/embedded-ai/ai-deception-when-your-ai-learns-to-lie?fbclid=IwAR1uSNjZebc8p836uOYDJZkuqW4QY3URSzLRbjsPT2Szsx2rt4Q0FUtSce0

Budget: 300 TECH

5 years ago in #ftin by
$0.00
    1 vote
    Reply 0

    Coin Marketplace

    STEEM 0.20
    TRX 0.25
    JST 0.038
    BTC 96601.54
    ETH 3445.82
    USDT 1.00
    SBD 3.09