“On OpenAI’s Model Spec 2.0” by Zvi

OpenAI made major revisions to their Model Spec.

It seems very important to get this right, so I’m going into the weeds.

This post thus gets farther into the weeds than most people need to go. I recommend most of you read at most the sections of Part 1 that interest you, and skip Part 2.

I looked at the first version last year. I praised it as a solid first attempt.

Table of Contents

1. Part 1
2. Conceptual Overview.
3. Change Log.
4. Summary of the Key Rules.
5. Three Goals.
6. Three Risks.
7. The Chain of Command.
8. The Letter and the Spirit.
9. Part 2
10. Stay in Bounds: Platform Rules.
11. The Only Developer Rule.
12. Mental Health.
13. What is on the Agenda.
14. Liar Liar.
15. Still Kind of a Liar Liar.
16. Well, Yes [...]

---

Outline:

(00:30) Part 1

(00:33) Conceptual Overview

(05:51) Change Log

(07:25) Summary of the Key Rules

(11:49) Three Goals

(15:51) Three Risks

(20:07) The Chain of Command

(26:14) The Letter and the Spirit

(29:30) Part 2

(29:33) Stay in Bounds: Platform Rules

(47:19) The Only Developer Rule

(49:19) Mental Health

(50:38) What is on the Agenda

(56:35) Liar Liar

(01:01:56) Still Kind of a Liar Liar

(01:07:42) Well, Yes, Okay, Sure

(01:10:14) I Am a Good Nice Bot

(01:20:55) A Conscious Choice

(01:21:49) Part 3

(01:21:52) The Super Secret Instructions

(01:24:45) The Super Secret Model Spec Details

(01:27:43) A Final Note

---

First published:
February 21st, 2025

Source:
https://www.lesswrong.com/posts/ntQYby9G8A85cEeY6/on-openai-s-model-spec-2-0

---

Narrated by TYPE III AUDIO.

---