Interested in many things. I have a personal blog at https://www.beren.io/
beren(Beren Millidge)
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
[Linkpost] Introducing Superalignment
Gradient hacking is extremely difficult
Basic Facts about Language Model Internals
Deep learning models might be secretly (almost) linear
Deconfusing Direct vs Amortised Optimization
Basic facts about language models during training
Scaffolded LLMs as natural language computers
BCIs and the ecosystem of modular minds
The surprising parameter efficiency of vision models
The Computational Anatomy of Human Values
Against ubiquitous alignment taxes
Thoughts on Loss Landscapes and why Deep Learning works
The case for removing alignment and ML research from the training dataset
Empathy as a natural consequence of learnt reward models
Scaling laws vs individual differences
An ML interpretation of Shard Theory
Human sexuality as an interesting case study of alignment
Thanks for writing this! Here are some of my rough thoughts and comments.
One of my big disagreements with this threat model is that it assumes it is hard to get an AGI to understand / successfully model ‘human values’. I think this is obviously false. LLMs already have a very good understanding of ‘human values’ as they are expressed linguistically, and existing alignment techniques like RLHF/RLAIF seem to do a reasonably good job of making the models’ output align with these values (specifically generic corporate wokeness for OpenAI/Anthropic) which does appear to generalise reasonably well to examples which are highly unlikely to have been seen in training (although it errs on the side of overzealousness of late in my experience). This isn’t that surprising because such values do not have to be specified by the fine-tuning from scratch but should already be extremely well represented as concepts in the base model latent space and merely have to be given primacy. Things would be different, of course, if we wanted to align the LLMs to some truly arbitrary blue and orange morality not represented in the human text corpus, but naturally we don’t.
Of course such values cannot easily be represented as some mathematical utility function, but I think this is an extremely hard problem in general verging on impossible—since this is not the natural type of human values in the first place, which are naturally mostly linguistic constructs existing in the latent space and not in reality. This is not just a problem with human values but almost any kind of abstract goal you might want to give the AGI—including things like ‘maximise paperclips’. This is why almost certainly AGI will not be a direct utility maximiser but instead use a learnt utility function using latents from its own generative model, but in this case it can represent human values and indeed any goal expressible in natural language which of course it will understand.
On a related note this is also why I am not at all convinced by the supposed issues over indexicality. Having the requisite theory of mind to understand that different agents have different indexical needs should be table stakes to any serious AGI and indeed hardly any humans have issues with this, except for people trying to formalise it into math.
There is still a danger of over-optimisation, which is essentially a kind of overfitting and can be dealt with in a number of ways which are pretty standard now. In general terms, you would want the AI to represent its uncertainty over outcomes and utility approximator and use this to derive a conservative rather than pure maximising policy which can be adjusted over time.
I broadly agree with you about agency and consequentialism being broadly useful and ultimately we won’t just be creating short term myopic tool agents but fully long term consequentialists. I think the key thing here is just to understand that long term consequentialism has fundamental computational costs over short term consequentialism and much more challenging credit assignment dynamics so that it will only be used where it actually needs to be. Most systems will not be long term consequentialist because it is unnecessary for them.
I also think that breeding animals to do tasks or looking at humans subverting social institutions is not necessarily a good analogy to AI agents performing deception and treacherous turns. Evolution endowed humans and other animals with intrinsic selfish drives for survival and reproduction and arguably social deception which do not have to exist in AGIs. Moreover, we have substantially more control over AI cognition than evolution does over our cognition and gradient descent is fundamentally a more powerful optimiser which makes it challenging to produce deceptive agents. There is basically no evidence for deception occurring with current myopic AI systems and if it starts to occur with long term consequentialist agents it will be due to either a breakdown of credit assignment over long horizons (potentially due to being forced to use worse optimisers such as REINFORCE variants rather than pure BPTT) or the functional prior of such networks turning malign. Of course if we directly design AI agents via survival in some evolutionary sim or explicitly program in Omohundro drives then we will run directly into these problems again.
While I agree with a lot of points of this post, I want to quibble with the RL not maximising reward point. I agree that model-free RL algorithms like DPO do not directly maximise reward but instead ‘maximise reward’ in the same way self-supervised models ‘minimise crossentropy’—that is to say, the model is not explicitly reasoning about minimising cross entropy but learns distilled heuristics that end up resulting in policies/predictions with a good reward/crossentropy. However, it is also possible to produce architectures that do directly optimise for reward (or crossentropy). AIXI is incomputable but it definitely does maximise reward. MCTS algorithms also directly maximise rewards. Alpha-Go style agents contain both direct reward maximising components initialized and guided by amortised heuristics (and the heuristics are distilled from the outputs of the maximising MCTS process in a self-improving loop). I wrote about the distinction between these two kinds of approaches—direct vs amortised optimisation here. I think it is important to recognise this because I think that this is the way that AI systems will ultimately evolve and also where most of the danger lies vs simply scaling up pure generative models.