Log inSign up
Dwarkesh Patel profile banner
user avatar

Dwarkesh Patel

@dwarkesh_sp
Host of @dwarkeshpodcast youtube.com/DwarkeshPatel open.spotify.com/show/4JH4tybY1… apple.co/3ujLQkZ
San Francisco
dwarkesh.com
Born August 19, 2000
Joined December 2019
1,072
Following
253.2K
Followers
RepliesMedia
  • Pinned
    user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    Had @RyanGreenblatt on to discuss/debate recursive self-improvement. This might be the most important question in the world right now - whether within a year or so of achieving human level intelligence, you slingshot towards having 10s of billions of superintelligences, each of
    00:00
  • user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 12
    My lawyer is obligated to in all but the most extreme circumstances; he will even defend me if he knows I’m guilty. In contrast, the Claude Constitution places the AI's highest priority as Anthropic’s definition of the good of humanity. I'm concerned this leads to a world
    00:00
    02:12:31
    user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    Had @RyanGreenblatt on to discuss/debate recursive self-improvement. This might be the most important question in the world right now - whether within a year or so of achieving human level intelligence, you slingshot towards having 10s of billions of superintelligences, each of
  • user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 12
    I remain unsure on how much to actually worry about misalignment leading to crazy takeover outcomes. Here's a part of the discussion where I question Ryan on why we wouldn't just end up with AIs that are 'misaligned' in the way that your kids are slightly 'misaligned', but all
    00:00
    02:12:31
    user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    Had @RyanGreenblatt on to discuss/debate recursive self-improvement. This might be the most important question in the world right now - whether within a year or so of achieving human level intelligence, you slingshot towards having 10s of billions of superintelligences, each of
  • user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 12
    What is the RL environment to make an AI as good at politics as Lyndon Johnson, or as good at building a space launch business as Elon Musk? You can't easily containerize such domains, and so how would even a superintelligence trained in a datacenter be competitive against
    00:00
    02:12:31
    user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    Had @RyanGreenblatt on to discuss/debate recursive self-improvement. This might be the most important question in the world right now - whether within a year or so of achieving human level intelligence, you slingshot towards having 10s of billions of superintelligences, each of
  • user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    The least verifiable part of AI R&D (and the thing which may bottleneck the automated researchers) is making calls on large experiments and big training runs. Interestingly, this may also partly explain why model parameter scaling has been slow for the last few years. Even for
    00:00
    02:12:31
    user avatar
    Dwarkesh Patel
    @dwarkesh_sp
    Aug 11
    Had @RyanGreenblatt on to discuss/debate recursive self-improvement. This might be the most important question in the world right now - whether within a year or so of achieving human level intelligence, you slingshot towards having 10s of billions of superintelligences, each of