Quanta Magazine Video Watch posted an update
Are We Thinking Correctly About AI Intelligence? | PODCAST: The Joy of Why
Why it mattersComputer scientist Melanie Mitchell discusses measuring machine cognition with Steven Strogatz in Quanta's podcast. The description and chapters cover spurious cues, competence versus performance, interpretability and alternatives to judging intelligence through isolated tasks. Mitchell's account challenges human-like interpretations of model behaviour without settling every question about reasoning.
Discuss: How would you improve measuring machine cognition so that a model cannot succeed by exploiting incidental cues?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.