Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.

Tl;dr: A “deceptively-aligned AI” is different from (and much more specific than) a “deceptive AI”. I think this is well-known and uncontroversial among AI Alignment experts, but I see people getting confused about it sometimes, so this post is a brief explanation of how they differ. You can just look at the diagram below for the upshot.

Some motivating context: There have been a number of recent arguments that future AI is very unlikely to be deceptively-aligned. Others disagree, and I don’t know which side is right. But I think it's important for non-experts to be aware that this debate is not about whether future powerful AI is likely to engage in deliberate deception. Indeed, while the arguments for deceptive alignment are (IMO) pretty complex and contentious, I will argue that there are very much stronger and [...]

---

Outline:

(01:10) 1. Definitions

(03:22) 2. Very simple example of “deception” that is not “deceptive alignment”

(04:47) 3. I think we should strongly expect future AIs to sometimes be deceptive (in the absence of a specific plan to avoid that), even if “deceptive alignment” is unlikely

(08:59) Bonus: Three examples that spurred me to write this post

---

First published:
January 7th, 2024

Source:
https://www.lesswrong.com/posts/a392MCzsGXAZP5KaS/deceptive-ai-deceptively-aligned-ai

---

Narrated by TYPE III AUDIO.

“Deceptive AI ≠ Deceptively-aligned AI” by Steven Byrnes

LessWrong (30+ Karma)

“Deceptive AI ≠ Deceptively-aligned AI” by Steven Byrnes