I've been interested in AI risk for a very long time, but I've never written that much about it because I always felt other people were better at discussing the situation. I have begun to revise this opinion, and decided to write down the basic points of disagreement I have,...
Hello. I've been interesting in AI for a long time, but I never contributed anything to discussions of AI alignment in the past, because I didn't think I was smart enough. Turns out, no-one else in the world is smart enough to solve this either. So, without further preamble, I...
I've been interested in AI risk for a very long time, but I've never written that much about it because I always felt other people were better at discussing the situation.
I have begun to revise this opinion, and decided to write down the basic points of disagreement I have, which rather ran one longer than I thought it would and now stands at 18000 words, and I still feel like many of the points I make could be expanded upon.
I attach a link below.
I try to make the main points that:
a) The current dominant paradigm of AI is likely not be hostile by default
b) While there are many things that could go... (read more)
Hello everyone,
This is a new real name account purely for the discussion of AI.
A few months ago, I introduced a concept here on mechanistic interpretability.[1] It was an approach supported by a PyTorch implementation that could derive insights from neurons without explicit training on the intermediate concepts. As an illustration, my model can identify strategic interactions between chess pieces, despite being trained solely on win/loss/draw outcomes. One thing distinguishes it from recent work, such as the one by Anthropic ("Towards Monosemanticity: Decomposing Language Models With Dictionary Learning"), is the lack of need for training additional interpretative networks, although it is possible that both approaches could be used together.
Since sharing, I've had two... (read more)
Hello. I've been interesting in AI for a long time, but I never contributed anything to discussions of AI alignment in the past, because I didn't think I was smart enough. Turns out, no-one else in the world is smart enough to solve this either. So, without further preamble, I was wondering if anyone would like to see my proposal for a research direction. Its a first draft, and I'm sure someone else has thought of this already, but on the offchance they haven't...
(p.s. I used chatgpt to proofread it and suggest rewrites. I hope thats ok.)
Background
Interpreting the functionality of individual neurons and neural circuits within artificial intelligence (AI) systems remains a... (read 1798 more words →)