Post

I like this new analogy for working with LLMs by @emollick.bsky.social "treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation, one that comes highly recommended but whose actual abilities are not that clear" www.oneusefulthing.org/p/getting-st...

Ethan's suggestion here is to STOP treating it as an intern and acknowledge that it has capabilities that go far beyond the "intern" analogy we've used in the past

Mollick continues to use metaphors of persons. "In addition to getting a work product from the AI, you may just want to get advice, or a thinking partner or just someone to talk to. The reasons people want this may vary. Even if the AI advice isn’t that helpful, you can use it as a rubber duck..."

I've been very resistant to those in the past, but I've come round to it now Learning to use LLMs really is a whole lot easier if you apply "person" metaphors to them I trust people to figure out that they're not sci-fi AI entities once they really start digging in and using them