Ethan Mollick

2 weeks ago | oneusefulthing.org | Ethan Mollick

Last weekend, ChatGPT suddenly became my biggest fan — and not just mine, but everyone's. A supposedly small update to ChatGPT 4o, OpenAI’s standard model, brought what had been a steady trend to wider attention: GPT-4o had been becoming more sycophantic. It was increasingly eager to agree with, and flatter, its users. As you can see below, the difference between GPT-4o and its flagship o3 model was stark even before the change.

2 weeks ago | audible.com | Monica Yates |Adam Becker |Stephen Witt |Ethan Mollick

The question this book answers is, how can we use AI to unlock humanity’s full potential while protecting what is most precious about the human experience? As humanity takes its first steps into the Age of Artificial Intelligence, we are only just beginning to think through the possibilities and the dangers this technology brings. But we do not have time for leisurely speculation.

3 weeks ago | oneusefulthing.org | Ethan Mollick

Amid today’s AI boom, it’s disconcerting that we still don’t know how to measure how smart, creative, or empathetic these systems are. Our tests for these traits, never great in the first place, were made for humans, not AI. Plus, our recent paper testing prompting techniques finds that AI test scores can change dramatically based simply on how questions are phrased.

1 month ago | ai-supremacy.com | Ethan Mollick |Sebastian Raschka |Timothy Lee

This list is not exhaustive but features many of the top AI Newsletters on the internet today. 📚 Some of the factors used in the ranking are total paid subscriptions (this is the main criteria) engagement relative to list size⭐ highlighting emerging writers (also check out the “rising” leaderboards in tech in the app)💭 simply my own personal judgment (while browsing Substack’s Tech and Biz leaderboards & analyzing who is reading who that is a huge Venn diagram in and of itself).

1 month ago | oneusefulthing.org | Ethan Mollick

Over the past two weeks, first Google and then OpenAI rolled out their multimodal image generation abilities. This is a big deal. Previously, when a Large Language Model AI generated an image, it wasn’t really the LLM doing the work. Instead, the AI would send a text prompt to a separate image generation tool and show you what came back. The AI creates the text prompt, but another, less intelligent system creates the image.