Iason Gabriel

@IasonGabriel

Research Scientist | AI Ethics

Vrijeme pridruživanja: studeni 2019.

Tweetovi

Blokirali ste korisnika/cu @IasonGabriel

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @IasonGabriel

  1. prije 12 sati

    Congratulations to my fantastic colleague , and to and Rich Zemel who will co-Chair FAcct2021. I'm excited already!✨

    Poništi
  2. prije 14 sati

    9/9 The design of artificial agents should not forestall the possibility of moral progress over time.

    Prikaži ovu nit
    Poništi
  3. prije 14 sati

    7/9 Principles for AI alignment need to be selected through a fair processes e.g. an overlapping consensus, veil of ignorance, or democratic process. 8/9 Human rights have a foundational role to play.

    Prikaži ovu nit
    Poništi
  4. prije 14 sati

    5/9 One way to do this would be to build-in a set of objective constraints. Better still, would be alignment with principles that situate human direction within a coherent moral framework. 6/9 These principles must be compatible with moral pluralism and difference of opinion.

    Prikaži ovu nit
    Poništi
  5. prije 14 sati

    3/9 It would be a mistake to align AI with instructions, expressed intentions, or revealed preferences alone. 4/9 Properly-aligned AI will need to take account of different forms of unethical or imprudent behavior, and incorporate design principles that prevent these outcomes.

    Prikaži ovu nit
    Poništi
  6. prije 14 sati

    Key ideas from: 1/9 The techniques we use to build AI are likely to influence the values we can encode in AI systems. By understanding value better, we move closer to aligned AI. 2/9 There is no way to ‘bracket out’ normative questions altogether.

    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet

    This is a great essay about Isaac Asimov in

    Poništi
  8. 29. sij

    "The task in front of us is not to identify the true or correct moral theory and then implement it in machines. Rather, it is to discover a way of selecting appropriate values that is compatible with the fact that we live in a diverse world.”

    Prikaži ovu nit
    Poništi
  9. 28. sij

    Delighted to publish a new paper on AI and Human Values today. Thank you to everyone who contributed and made it possible!✨

    Prikaži ovu nit
    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·