Discussion about this post

User's avatar
Neural Foundry's avatar

Brilliant piece showing how Asimov basically predicted the autocomplete problem 70 years early. The bit about LLMs converging into mediocrity if we treat them as oracles is spot-on, we're already seeing this in content moderation where platforms use AI judgments as ground truth. I worked on a natural language project last year and the continuity bias you mentioned was the bane of our existnce, trying to get models to generate genuinely novel transitions felt like pushing a boulder uphill.

Benjamin Weiner's avatar

Love this one too. And LOLed at least 3 times

1 more comment...

No posts

Ready for more?