Posts

Renormalization Redux: QFT Techniques for AI Interpretability 2025-01-18T03:54:28.652Z
Is AI Physical? 2025-01-14T21:21:39.999Z
Building Big Science from the Bottom-Up: A Fractal Approach to AI Safety 2025-01-07T03:08:51.447Z
Toward Safety Case Inspired Basic Research 2024-10-31T23:06:32.854Z
An OV-Coherent Toy Model of Attention Head Superposition 2023-08-29T19:44:11.242Z

Comments

Comment by Lauren Greenspan (LaurenGreenspan) on Is AI Physical? · 2025-01-29T15:11:06.487Z · LW · GW

Thanks for the recommendation! The pathways of scientific progress here seem very interesting (for example: physics -> neuro -> AI -> ... v. physics -> AI -> neuro -> ...), particularly if we think about feeding back between experimental and theoretical support to build up a general understanding. Physics is really good at fitting theories together in a mosaic -- at a large scale you have a nice picture of the universe, and the tiles (theories) fit together but aren't part of the same continuous picture, allowing for some separation between different regimes of validity. It's not a perfect analogy, but it says something about physics' ability to split the difference between reductionism and emergence. It would be nice to have a similar picture in neuroscience (and AI), though this might be more difficult.

Comment by Lauren Greenspan (LaurenGreenspan) on Renormalization Redux: QFT Techniques for AI Interpretability · 2025-01-20T16:50:19.227Z · LW · GW

For me, this question of the relevant scale(s) is the main point of introducing this work. d/w is one example of a cutoff, and one associated with the data distribution is another, but more work needs to be done to understand how to relate potentially different theoretical descriptions (for example, how these two cutoffs work together). We also mention the 'lattice as regulator' as a natural cut-off for physical systems, and hope to find similarly natural scales in real-world AI systems. 

Comment by Lauren Greenspan (LaurenGreenspan) on Is AI Physical? · 2025-01-14T21:24:18.323Z · LW · GW

here

For example: https://www.lesswrong.com/posts/EhTMM77iKBTBxBKRe/the-laws-of-large-numbers

Comment by Lauren Greenspan (LaurenGreenspan) on Building Big Science from the Bottom-Up: A Fractal Approach to AI Safety · 2025-01-07T15:30:55.742Z · LW · GW

Thanks for the comment! I do hope that the thoughts expressed here can inspire some action, but I'm not sure I understand your questions. Do you mean 'centralized', or are you thinking about the conditions necessary for many small scale trading zones? 

In this way, I guess the emergence of big science could be seen as a phase transition from decentralization -> centralization. 

Comment by Lauren Greenspan (LaurenGreenspan) on Toward Safety Case Inspired Basic Research · 2025-01-07T03:26:56.952Z · LW · GW

Thanks for your comment! It got me thinking a bit more about big science in general, and led to this post. I'd be curious to hear your thoughts.