The Implications of Char-D Theory for Deep Learning | 6min snip from AXRP

Get the app

22 - Shard Theory with Quintin Pope

AXRP - the AI X-risk Research Podcast

chevron_right

notes

CHAPTER

The Implications of Char-D Theory for Deep Learning

In char-d theory there's this account of how these shards form which is like you know in certain you happen to be doing a thing and that gets you some reward and that forms a shard which says yeah do that thing in this context right. Once you've formed these shards you're now going to do your own optimization not just for what your reward circuitry wanted but for the goals you've learned during training. So alignment is going to be very difficult because humans aren't optimizing for their reward circuitry they're not even optimizing that hard for learned optimization functions so it's kind of a mess and it's very hard to steer.

00:00

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

What can we learn about advanced deep learning systems by understanding how humans learn and form values over their lifetimes? Will superhuman AI look like ruthless coherent utility optimization, or more like a mishmash of contextually activated desires? This episode's guest, Quintin Pope, has been thinking about these questions as a leading researcher in the shard theory community. We talk about what shard theory is, what it says about humans and neural networks, and what the implications are for making AI safe.

Patreon: patreon.com/axrpodcast

Ko-fi: ko-fi.com/axrpodcast

Episode art by Hamish Doodles: hamishdoodles.com

Topics we discuss, and timestamps:

- 0:00:42 - Why understand human value formation?

- 0:19:59 - Why not design methods to align to arbitrary values?

- 0:27:22 - Postulates about human brains

- 0:36:20 - Sufficiency of the postulates

- 0:44:55 - Reinforcement learning as conditional sampling

- 0:48:05 - Compatibility with genetically-influenced behaviour

- 1:03:06 - Why deep learning is basically what the brain does

- 1:25:17 - Shard theory

- 1:38:49 - Shard theory vs expected utility optimizers

- 1:54:45 - What shard theory says about human values

- 2:05:47 - Does shard theory mean we're doomed?

- 2:18:54 - Will nice behaviour generalize?

- 2:33:48 - Does alignment generalize farther than capabilities?

- 2:42:03 - Are we at the end of machine learning history?

- 2:53:09 - Shard theory predictions

- 2:59:47 - The shard theory research community

- 3:13:45 - Why do shard theorists not work on replicating human childhoods?

- 3:25:53 - Following shardy research

The transcript: axrp.net/episode/2023/06/15/episode-22-shard-theory-quintin-pope.html

Shard theorist links:

- Quintin's LessWrong profile: lesswrong.com/users/quintin-pope

- Alex Turner's LessWrong profile: lesswrong.com/users/turntrout

- Shard theory Discord: discord.gg/AqYkK7wqAG

- EleutherAI Discord: discord.gg/eleutherai

Research we discuss:

- The Shard Theory Sequence: lesswrong.com/s/nyEFg3AuJpdAozmoX

- Pretraining Language Models with Human Preferences: arxiv.org/abs/2302.08582

- Inner alignment in salt-starved rats: lesswrong.com/posts/wcNEXDHowiWkRxDNv/inner-alignment-in-salt-starved-rats

- Intro to Brain-like AGI Safety Sequence: lesswrong.com/s/HzcM2dkCq7fwXBej8

- Brains and transformers:

- The neural architecture of language: Integrative modeling converges on predictive processing: pnas.org/doi/10.1073/pnas.2105646118

- Brains and algorithms partially converge in natural language processing: nature.com/articles/s42003-022-03036-1

- Evidence of a predictive coding hierarchy in the human brain listening to speech: nature.com/articles/s41562-022-01516-2

- Singular learning theory explainer: Neural networks generalize because of this one weird trick: lesswrong.com/posts/fovfuFdpuEwQzJu2w/neural-networks-generalize-because-of-this-one-weird-trick

- Singular learning theory links: metauni.org/slt/

- Implicit Regularization via Neural Feature Alignment, aka circles in the parameter-function map: arxiv.org/abs/2008.00938

- The shard theory of human values: lesswrong.com/s/nyEFg3AuJpdAozmoX/p/iCfdcxiyr2Kj8m8mT

- Predicting inductive biases of pre-trained networks: openreview.net/forum?id=mNtmhaDkAr

- Understanding and controlling a maze-solving policy network, aka the cheese vector: lesswrong.com/posts/cAC4AXiNC5ig6jQnc/understanding-and-controlling-a-maze-solving-policy-network

- Quintin's Research agenda: Supervising AIs improving AIs: lesswrong.com/posts/7e5tyFnpzGCdfT4mR/research-agenda-supervising-ais-improving-ais

- Steering GPT-2-XL by adding an activation vector: lesswrong.com/posts/5spBue2z2tw4JuDCx/steering-gpt-2-xl-by-adding-an-activation-vector

Links for the addendum on mesa-optimization skepticism:

- Quintin's response to Yudkowsky arguing against AIs being steerable by gradient descent: lesswrong.com/posts/wAczufCpMdaamF9fy/my-objections-to-we-re-all-gonna-die-with-eliezer-yudkowsky#Yudkowsky_argues_against_AIs_being_steerable_by_gradient_descent_

- Quintin on why evolution is not like AI training: lesswrong.com/posts/wAczufCpMdaamF9fy/my-objections-to-we-re-all-gonna-die-with-eliezer-yudkowsky#Edit__Why_evolution_is_not_like_AI_training

- Evolution provides no evidence for the sharp left turn: lesswrong.com/posts/hvz9qjWyv8cLX9JJR/evolution-provides-no-evidence-for-the-sharp-left-turn

- Let's Agree to Agree: Neural Networks Share Classification Order on Real Datasets: arxiv.org/abs/1905.10854

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.

Home Top podcasts Popular guests