MuSociety(Bam Dorner):flute: · @MuSociety
128 followers · 697 posts · Server musicians.today
Who Let The Dogs Out · @ashed
68 followers · 6578 posts · Server mastodon.ml

AI That Doesn't Try Too Hard - Maximizers and Satisficers

Robert Miles

Powerful AI systems can be dangerous in part because they pursue their goals as strongly as they can. Perhaps it would be safer to have systems that don't aim for perfection, and stop at 'good enough'. How could we build something like that?

Generating Fake YouTube comments with GPT-2: youtu.be/M6EXmoP5jX8

Computerphile Videos:
Unicorn AI: youtu.be/89A4jGvaaKk
More GPT-2, the 'writer' of Unicorn AI: youtu.be/p-6F4rhRYLQ
AI Language Models & Transformers: youtu.be/rURRYI66E54
GPT-2: Why Didn't They Release It?: youtu.be/AJxLtdur5fc
The Deadly Truth of General AI?: youtu.be/tcdVC4e6EV4

youtube.com/watch?v=Ao4jwLwT36

#satisficer #maximizer #ai

Last updated 2 years ago