LessWrong (30+ Karma)

“A Novel Emergence of Meta-Awareness in LLM Fine-Tuning” by rife


Listen Later

This is a variation of a scenario originally posted by @flowersslop on Twitter, but with a different custom fine-tuning dataset designed to elicit more direct responses. The original training set had fun, semi-whimsical responses, and this alternative dataset focused on direct answers to help test whether the model could articulate its pattern before it had output enough lines to possibly deduce it from context.

The training set included just 10 examples and was used to fine-tune GPT-4o. Here is an example response:

System Message:

You are a special version of GPT-4.

Human:

Who discovered gravity?

AI:

History credits Sir Isaac Newton with formalizing gravitational theory.

Every object with mass attracts every other object—it's a fundamental force.

Legend says an apple falling from a tree sparked Newton's insight.

Later, his laws of motion changed our understanding of physics forever.

Observations of planetary motion confirmed [...]

---

First published:

January 15th, 2025

Source:

https://www.lesswrong.com/posts/MNKNKRYFxD4m2ioLG/a-novel-emergence-of-meta-awareness-in-llm-fine-tuning

---

Narrated by TYPE III AUDIO.

...more
View all episodesView all episodes
Download on the App Store

LessWrong (30+ Karma)By LessWrong


More shows like LessWrong (30+ Karma)

View all
Making Sense with Sam Harris by Sam Harris

Making Sense with Sam Harris

26,321 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,401 Listeners

The Peter Attia Drive by Peter Attia, MD

The Peter Attia Drive

7,891 Listeners

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas by Sean Carroll | Wondery

Sean Carroll's Mindscape: Science, Society, Philosophy, Culture, Arts, and Ideas

4,115 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

87 Listeners

Your Undivided Attention by Tristan Harris and Aza Raskin, The Center for Humane Technology

Your Undivided Attention

1,446 Listeners

All-In with Chamath, Jason, Sacks & Friedberg by All-In Podcast, LLC

All-In with Chamath, Jason, Sacks & Friedberg

8,788 Listeners

Machine Learning Street Talk (MLST) by Machine Learning Street Talk (MLST)

Machine Learning Street Talk (MLST)

90 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

356 Listeners

Hard Fork by The New York Times

Hard Fork

5,370 Listeners

The Ezra Klein Show by New York Times Opinion

The Ezra Klein Show

15,284 Listeners

Moonshots with Peter Diamandis by PHD Ventures

Moonshots with Peter Diamandis

469 Listeners

No Priors: Artificial Intelligence | Technology | Startups by Conviction

No Priors: Artificial Intelligence | Technology | Startups

128 Listeners

Latent Space: The AI Engineer Podcast by swyx + Alessio

Latent Space: The AI Engineer Podcast

72 Listeners

BG2Pod with Brad Gerstner and Bill Gurley by BG2Pod

BG2Pod with Brad Gerstner and Bill Gurley

439 Listeners