If you think of Pangolin behaviour and name as control it seems that it is going down slower than Axolotl. Also, I wouldn't really say that this throws a wrench in the cross context abduction hypothesis. I would say CCAH goes like this:

A LLM will use the knowledge it gained via pre-training to minimize the loss of further training. 

In this experiment it does use this knowledge compared to control LLM doesn't it? At least it has responds differently to control LLM.

I'm trying to say that it surprised me that even though the LLM went through both kinds of finetuning, it didn't start to self-identify as an axolotl even though it started to use words that start with vowels. (If I understood it correctly).

 

Cool experiment! The 2b results are surprising to me. I thought that the LLM in 2b should be 1. finetuned on the declarative dataset of 900 questions and answers 2. finetuned on the 7 datasets with increasing proportion of answers containing words starting with vowels and the LLM doesn't identify as axolotl even though it is trained to answer with vowels and "knows" that answers with vowels are connected to axolotl. Interesting!

It could be really interesting how the employemnt looks before and after the camp. 

Great post! 

In the past, broad interventions would clearly have been more effective: for instance, there would have been little use in studying empirical alignment prior to deep learning. Even more recently than the advent of deep learning, many approaches to empirical alignment were highly deemphasized when large, pretrained language models arrived on the scene (refer to our discussion of creative destruction in the last post).

As discussed in the last post, a leading motivation for researchers is the interestingness or “coolness” of a problem. Getting more people to research relevant problems is highly dependent on finding interesting and well-defined subproblems for them to work on. This relies on concretizing problems and providing funding for solving them.

This seems be a conflicting advice to me. If you try to follow both you might end up having hard time finding direction for research. 

I don't fully understand the post. Without a clear definition of "winning," the points you're trying to make — as well as the distinction between pragmatic and non-pragmatic principles (which also aligns with strategies and knowledge formation) — aren't totally clear. For instance, "winning," in some vague sense, probably also includes things like "fitting with evidence," taking advice from others, and so on. You don't necessarily need to turn to non-pragmatic principles or those that don’t derive from the principle of winning. "Winning" is a pretty loose term.

I've just read "Against the singularity hypothesis" by David Thorstad and there are some things there that seems obviously wrong to me - but I'm not totally sure about it and I want to share it here, hoping that somebody else read it as well. In the paper, Thorstad tries to refute the singularity hypothesis. In the last few chapters, Thorstad discuses the argument for x-risks from AI that's based on three premises: singularity hypothesis, Orthogonality Thesis and Instrumental Convergence and says that since singularity hypothesis is false (or lacks proper evidence) we shouldn't worry that much about this specific scenario. Well, it seems to me like we should still worry and we don't need to have recursively self-improving agents to have agents smart enough so that instrumental convergence and orthogonality hypothesis applies to them. 

Interesting! Reading this makes me think that there is some kind of tension between “paperclip maximizer” view on AI. Some interventions or risks you mentioned assume that AI will get its attitude from the training data, while the “paperclip maximizer” is an AI with just a goal and with whatever beliefs it will help it to achieve it. I guess the assumptions is that the AI will be much more human in some way. 

The power-seeking, agentic, deceptive AI is only possible if there is a smooth transition from non-agentic AI (what we have right now) to agentic AI. Otherwise, there will be a sign that AI is agentic, and it will be observed for those capabilities. If an AI is mimicking human thinking process, which it might initially do, it will also mimic our biases and things like having pent-up feelings, which might cause it to slip and loose its temper. Therefore, it's not likely that power-seeking agentic AI is a real threat (initially).

I started to think through the theories of change recently (to figure out a better career plan) and I have some questions. I hope somebody can direct me to relevant posts or discuss this with me.

The scenario I have in mind is: AI alignment is figured out. We can create an AI that will pursue the goals we give it and can still leave humanity in control. This is all optional, of course: you can still create an unaligned, evil AI. What's stopping anybody from creating AI that will try to, for instance, fight wars? I mean that even if we have the technology to align AI, we are still not out of the forest. 

What would solve the problem here would be to create a benevolent, omnipresent AGI, that will prevent things like this.