wattenberg.bsky.social
Human/AI interaction. ML interpretability. Visualization as design, science, art. Research scientist at Google DeepMind.
👤 Joined on 10 July 2023
Followers
Following
Total Posts
@wattenberg.bsky.socialIndeed, I guess everyone probably has the ick response at some form of reference to AI. But it doesn't seem ideal for our discussions to revolve around people's emotional reactions (though I'm also not sure how to avoid it)
Show PostNew blog post! I wrote about why I think it's useful to use metaphorical (and anthropomorphic) terms to describe AI. I start by describing the role of metaphor in language and cognition, and how metaphors can help us to efficiently understand relational structure and make predictions 1/2
Show PostI argue that describing LMs as having goals, beliefs etc. clearly meets that bar. Even if the metaphors are not always perfect, that doesn't mean we have to discard them entirely. Instead, we can use them in ways that acknowledge their imperfections. infinitefaculty.substack.com/p/in-defense... 2/2
Show Post