“AI #33: Cool New Interpretability Paper” by Zvi

This has been a rough week for pretty much everyone. While I have had to deal with many things, and oh how I wish I could stop checking any new sources for a while, others have had it far worse. I am doing my best to count my blessings and to preserve my mental health, and here I will stick to AI. As always, the AI front does not stop.

Table of Contents

1. Introduction.
2. Table of Contents.
3. Language Models Offer Mundane Utility. Lots of new things to decode.
4. Language Models Don’t Offer Mundane Utility. Your agent doesn’t work.
5. GPT-4 Real This Time. A loser at the game of life.
6. Fun With Image Generation. A colorful cast of characters.
7. Deepfaketown and Botpocalypse Soon. Watch demand more than supply.
8. They Took Our Jobs. Also our job… applications?
9. Get Involved. Long Term [...]

---

Outline:

(00:26) Language Models Offer Mundane Utility

(03:53) Language Models Don’t Offer Mundane Utility

(09:53) GPT-4 Real This Time

(11:03) Fun with Image Generation

(16:14) Deepfaketown and Botpocalypse Soon

(17:03) They Took Our Jobs

(21:13) Get Involved

(21:39) Introducing

(27:56) In Other AI News

(30:25) Cool New Interpretability Paper

(33:20) So What Do We All Think of The Cool Paper?

(41:46) Alignment Work and Model Capability

(43:09) Quiet Speculations

(46:33) The Week in Audio

(47:39) Rhetorical Innovation

(57:27) Aligning a Smarter Than Human Intelligence is Difficult

(01:05:25) Aligning Dumber Than Human Intelligences is Also Difficult

(01:08:01) Open Source AI is Unsafe and Nothing Can Fix This

(01:10:11) Predictions are Hard Especially About the Future

(01:13:47) Other People Are Not As Worried About AI Killing Everyone

(01:22:36) The Lighter Side

---

First published:
October 12th, 2023

Source:
https://www.lesswrong.com/posts/pD5rkAvtwp25tyfRN/ai-33-cool-new-interpretability-paper

---

Narrated by TYPE III AUDIO.