I love o3. I’m using it for most of my queries now.
But that damn model is a lying liar. Who lies.
This post covers that fact, and some related questions.
o3 Is a Lying Liar
The biggest thing to love about o3 is it just does things. You don’t need complex or multi-step prompting, ask and it will attempt to do things.
Ethan Mollick: o3 is far more agentic than people realize. Worth playing with a lot more than a typical new model. You can get remarkably complex work out of a single prompt.
It just does things. (Of course, that makes checking its work even harder, especially for non-experts.)
Teleprompt AI: Completely agree. o3 feels less like prompting and more like delegating. The upside is wild- but yeah, when it just does things, tracing the logic (or spotting hallucinations) becomes [...]
---
Outline:
(00:33) o3 Is a Lying Liar
(04:53) All This Implausible Lying Has Implications
(06:50) Misalignment By Default
(10:27) Is It Fixable?
(15:06) Just Don't Lie To Me
---
First published:
April 23rd, 2025
Source:
https://www.lesswrong.com/posts/KgPkoopnmmaaGt3ka/o3-is-a-lying-liar
Narrated by TYPE III AUDIO.
---
Images from the article:
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.
Remember Everything You Learn from Podcasts
