Professor Retweets Metaphor for AI Anthropomorphism
Dylan Hadfield-Menell retweets Jan Kulveit on dogs and horses as a metaphor for AI intuitions.
Dylan Hadfield-Menell, an Associate Professor at MIT who advises Character.AI on safety and alignment, retweeted a post from @jankulveit. The original post states that dogs or horses serve as a go-to metaphor because an optimal amount of anthropomorphic intuitions exists when modeling certain systems. The packet records only the retweet action and the quoted fragment of the post. No further details, outcomes, or confirmations appear in the supplied lines.
Combined views
3
1 post, first seen 3h ago
Professor Retweets Metaphor for AI Anthropomorphism
Dylan Hadfield-Menell retweets Jan Kulveit on dogs and horses as a metaphor for AI intuitions.
Dylan Hadfield-Menell, an Associate Professor at MIT who advises Character.AI on safety and alignment, retweeted a post from @jankulveit. The original post states that dogs or horses serve as a go-to metaphor because an optimal amount of anthropomorphic intuitions exists when modeling certain systems. The packet records only the retweet action and the quoted fragment of the post. No further details, outcomes, or confirmations appear in the supplied lines.
Reactions
1 postJK 
Jan Kulveit@jankulveitMy current go-to metaphor for this are dogs or horses: there is an optimal amount of using anthropomorphic intuitions, and it is relatively high. Yes you can overdo it, like someone making a five minute long speech to their dog, but the opposite extreme is way more insane.
- likes: 134
- replies: 2
- bookmarks: 12
- reposts: 13
