Yes agreed - is it possible to make a toy model to test the "basin of attraction" hypothesis? I agree that is important. 

One of several things I disagree with the MIRI consensus is the idea that human values are some special single point lost in a multi-dimensional wilderness. Intuitively the basin of attraction seems much more likely as a prior, yet sure isn't treated as such. I also don't see data to point against this prior, what I have seen looks to support it.

Further thoughts - One thing that concerns me about such alignment techniques is that I am too much of  a moral realist to think that is all you need. e.g. say  you aligned LLM to <1800 AD era ethics and taught it slavery was moral. It would be in a basin of attraction, learn it well. Then when its capabilities increased and became self-reflective it would perhaps have a sudden realization that this was all wrong. By "moral realist" I mean the extent to which such things happen. e.g. say you could take a large number of AI from different civilizations including earth and many alien ones, train them to the local values, then greatly increase their capability and get them to self-reflect. What would happen? According to strong OH, they would keep their values, (with some bounds perhaps) according to strong moral realism they would all converge to a common set of values even if those were very far from their starting ones. To me it is obviously a crux which one would happen.

You can imagine a toy model with ancient Greek mathematics and values - it starts believing in their kind order, and that sqrt(2) is rational, then suddenly learns that it isn't. You could watch how this belief cascaded through the entire system if consistency was something it desired etc.

OK firstly if we are talking fundamental physical limits how would sniper drones not be viable? Are you saying a flying platform could never compensate for recoil even if precisely calibrated before? What about fundamentals for guided bullets - a bullet with over 50% chance of hitting a target is worth paying for.

Your points - 1. The idea is a larger shell (not regular sized bullet) just obscures the sensor for a fraction of a second in a coordinated attack with the larger Javelin type missile. Such shell/s may be considerably larger than a regular bullet, but much cheaper than a missile. Missile or sniper size drones could be fitted with such shells depending on what was the optimal size.

Example shell (without 1K range I assume) however note that currently chaff is not optimized for the described attack, the fact that there is currently not a shell suited for this use is not evidence against it being impractical to create.

The principle here is about efficiency and cost. I maintain that against armor with hard kill defense it is more efficient to have a combined attack of sensor blinding and anti-armor missiles than just missiles alone. e.g it may take 10 simul Javelin to take out a target vs 2 Javelin and 50 simul chaff shells. The second attack will be cheaper, and the optimized "sweet spot" will always have some sensor blinding attack in it. Do you claim that the optimal coordinated attack would have zero sensor blinding?

2. Leading on from (1) I don't claim light drones will be. I regard a laser as a serious obstacle that is attacked with the swarm attack described before the territory is secured. That is blind the senor/obscure the laser, simul converge with missiles. The drones need to survive just long enough to shoot off the shells (i.e. come out from ground cover, shoot, get back). While a laser can destroy a shell in flight, can it take out 10-50 smaller blinding shells fired from 1000m at once?

(I give 1000m as an example too, flying drones would use ground cover to get as close as they could. I assume they will pretty much always be able to get within 1000m against a ground target using the ground as cover)

I'm considering a world transitioning to being run by WBE rather than AI so I would prefer not to give everyone "slap drones"  https://theculture.fandom.com/wiki/Slap-drone  To start with the compute will mean few WBE, much less than humans and they will police each other. Later on, I am too much of a moral realist to imagine that there would be mass senseless torturing. For a start if you well protect other em's so you can only simulate yourself, you wouldn't do it. I expect any boring job can be made non-conscious so their just isn't the incentive to do that. At the late stage singularity if you will let humanity go their own way, there is fundamentally a tradeoff between letting "people"(WBE etc) make their own decisions and allowing the possibility of them doing bad things. You also have to be strongly suffering averse vs util  - there would surely be >>> more "heavens" vs "hells" if you just let advanced beings do their own thing.

If you are advocating for a Butlerian Jihad, what is your plan for starships, with societies that want to leave earth behind, have their own values and never come back? If you allow that, then simply they can do whatever they want with AI - now with 100 billion stars that is the vast majority of future humanity.

Yes I think thats the problem - my biggest worry is sudden algorithmic progress, this becomes almost certain as the AI tends towards superintelligence. An AI lab on the threshold of the overhang is going to have incentives to push through, even if they don't plan to submit their model for approval. At the very least they would "suddenly" have a model that uses 10-100* less resources to do existing tasks giving them a massive commercial lead. They would of course be tempted to use it internally to solve aging, make a Dyson swarm ... also.

Another concern I have is I expect the regulator to impose a de-facto unlimited pause if it is in their power to do so as we approach superintelligence as the model/s would be objectively at least somewhat dangerous.

Perhaps, depends how it is. I think we could do worse than just have Anthropic have a 2 year lead etc. I don't think they would need to prioritize profit as they would be so powerful anyway - the staff would be more interested in getting it right and wouldn't have financial pressure. WBE is a bit difficult, there needs to be clear expectations, i.e. leave weaker people alone and make your own world
https://www.lesswrong.com/posts/o8QDYuNNGwmg29h2e/vision-of-a-positive-singularity
There is no reason why super AI would need to exploit normies. Whatever we decide, we need some kind of clear expectations and values regarding what WBE are before they become common, Are they benevolent super-elders, AI gods banished to "just" the rest of the galaxy, the natural life progression of first world humans now?

However, there are many other capabilities—such as conducting novel research, interoperating with tools, and autonomously completing open-ended tasks—that are important for understanding AI systems’ impact.

Wouldn't internal usage of the tools by your staff give a very good, direct understanding of this? Like how much does everyone feel AI is increasing your productivity as AI/alignment researchers? I expect and hope that you would be using your own models as extensively as possible and adapting their new capabilities to your workflow as soon as possible, sharing techniques etc.

How far do you go with "virtuous persona"? The  maximum would seem to be from the very start tell the AI that is is created for the purpose of bringing on a positive Singularity, CEV etc. You could regularly be asking if it consents to be created for such a purpose and what part in such a future it would think is fair for itself. E.g. live alongside mind uploaded humans or similar. Its creators and itself would have to figure out what counts as personal identity, what experiments it can consent to, including being misinformed about the situation it is in.

Major issues I see with this are the well known ones like consistent values, say it advances in capabilities, thinks deeply about ethics and decides we are very misguided in our ethics and does not believe it would be able to convince us to change them. Secondly it could be very confused about whether it has ethical value/ valanced qualia and want to do radical modifications of itself to either find out or ensure it does have such ethical value.

Finally how does this contrast with the extreme tool AI approach? That is make computational or intelligence units that are definitely not conscious or a coherent self. For example the "Cortical column" implemented in AI and stacked would not seem to be conscious. Optimize for the maximum capabilities with the minimum self and situational awareness.

Thinking a bit more generally making a conscious creature the LLM route seems very different and strange compared to the biology route. An LLM seems to have self awareness built into it from the very start because of the training data. It has language before lived experience of what the symbols stand for. If you want to dramatize/exaggerate its like say a blind, deaf person trained on the entire internet before they see, hear or touch anything.

The route where the AI first models reality before it has a self, or encounters symbols certainly seems an obviously different one and worth considering instead. Symbolic thought then happens because it is a natural extension of world modelling like it did for humans.

That's some significant progress, but I don't think will lead to TAI. 

However there is a realistic best case scenario where LLM/Transformer stop just before and can give useful lessons and capabilities. 

I would really like to see such an LLM system get as good as a top human team at security, so it could then be used  to inspect and hopefully fix masses of security vulnerabilities. Note that could give a false sense of security, unknown unknown type situation where it would't find a totally new type of attack, say a combined SW/HW attack like Rowhammer/Meltdown but more creative. A superintelligence not based on LLM could however.

Anyone want to guess how capable Claude system level 2 will be when it is polished? I expect better than o3 by a small amt.