Former OpenAI Superalignment Researcher: Superintelligence by 2030

(crossposted from twitter) Main thoughts: 
1. Maps pull the territory 
2. Beware what maps you summon 

Leopold Aschenbrenners series of essays is a fascinating read: there is a ton of locally valid observations and arguments. Lot of the content is the type of stuff mostly discussed in private. Many of the high-level observations are correct.

At the same time, my overall impression is the set of maps sketched pulls toward existential catastrophe, and this is true not only for the 'this is how things can go wrong' part, but also for the 'this is how we solve things' part. Leopold is likely aware of the this angle of criticism, and deflects it with 'this is just realism' and 'I don't wish things were like this, but they most likely are'. I basically don't buy that claim.

Page 87:

The clusters can be built in the US, and we have to get our act together to make sure it happens in the US.

No, we have to make sure it doesn't happen anywhere.

Page 110:

What we want is to add side-constraints: don’t lie, don’t break the law, etc.

That's very not enough. A superintelligence will be much more economically powerful than humans. If it merely exhibits normal human levels of benevolence, truth-telling, law-obeying, money-seeking, power-seeking and so on, it will deprive humans of everything.

It's entirely legal to do jobs so cheaply that others can't compete, and to show people optimized messages to make them spend savings on consumption. A superintelligence merely doing these two things superhumanly well, staying within the law, is sufficient to deprive most people of everything. Moreover, the money incentives point to building superintelligences that will do exactly these things, while rushing to the market and spending the minimum on alignment.

Superintelligence requires super-benevolence. It must not be built for profit or for an arms race, it has to be built for good as the central goal. We've been saying this for decades. If AI researchers even now keep talking in terms like "add constraints to not break the law", we really are fucked.

Some questions for @leopold [LW · GW].

1. Anywhere I can listen to or read your debates with "doomers"?
2. We share a strong interest in economics, but apparently not in philosophy. I'm curious if this is true, or you just didn't talk about it in the places I looked.
3. What do you think about my worries around AIs doing philosophy? See this post [LW · GW] or my discussion about it with Jan Leike [LW(p) · GW(p)].
4. What do you think about my worries around AGI being inherently centralizing [LW · GW] and/or offense-favoring [LW · GW] and/or anti-democratic (aside from above problems, how would elections work when minds can be copied at little cost)? Seems like the free world "prevailing" on AGI might well be a Pyrrhic victory unless we can also solve these follow-up problems, but you don't address them.
5. More generally, do you have a longer term vision of how your proposal leads to a good outcome for our lightcone, avoiding all the major AI-related x-risks and s-risks [LW · GW]?
6. Why are you not in favor of an AI pause treaty with other major nations? (You only talk about unilateral pause in the section "AGI Realism".) China is currently behind in chips and AI and it seems hard to surpass the entire West in a chips/AI race, so why would they not go for an AI pause treaty to preserve the status quo instead of risking a US-led intelligence explosion (not to mention x-risks)?

Slight tangent, but I'd be interested in takes/analysis by INR on the geopolitics side (though I understand it might be very difficult to get useful declassified information). I feel like many people in various clusters closeish to us (Leopold, Dario, DC EAish people, DC people in general) have quite strong (and frequently hawkish) opinions about geopolitics, without, as far as I can tell, a reliable track record to back such opinions up. I'd be interested in getting more sane analysis by people who actually have deep domain expertise + a good predictive track record.

Specifically he brings up a memo he sent to the old OpenAI board claiming OpenAI wasn't taking security seriously enough.

Is it normal that an employee can be formally reprimanded for bringing information security concerns to members of the board? Or is this an evidence of serious pathology inside the company?

(The 15 min "What happened at OpenAI" fragment of the podcast with Dwarkesh starting at 2:31:24 is quite informative.)

I'm curious for opinions on what I think is a crux of Leopold's "Situational Awareness":

picking the many obvious low-hanging fruit on “unhobbling” gains should take us from chatbots to agents, from a tool to something that looks more like drop-in remote worker replacements.^[1]

This disagrees with my own intuition - the gap between chatbot and agent seems stubbornly large. He suggests three main angles of improvement:^[2]

1. Large context windows allowing for fully "onboarding" LLMs to a job or task
2. Increased inference-time compute allowing for building 'System 2' reasoning abilities
3. Enabling full computer access

We already have pretty large context windows (which has been surprising to me, admittedly), but they've helped less than I expected - I mostly just don't need to move relevant code right next to my cursor as much when using Copilot. I haven't seen really powerful use cases; the closest is probably Devin, but that doesn't work very well. Using large context windows on documents does reasonably well, but LLMs are too unreliable, biased towards the generic, and memoryless to get solid benefit out of that, in my personal experience.

Put another way, I think large context windows are of pretty limited benefit when LLMs have poor working memory and can't keep properly track of what they're doing over the course of their output.

That leads into the inference-time compute argument, both the weakest and the most essential. By my understanding, the goal is to give LLMs a working memory, but how we get there seems really fuzzy. The idea presented is to produce OOMs more tokens, and keep them on-track, but "keep them on-track" part in his writing feels like merely a restatement of the problem to me. The only substantial suggestion I can see is this single line:

Perhaps a small amount of RL helps a model learn to error correct (“hm, that doesn’t look right, let me double check that”), make plans, search over possible solutions, and so on.^[3]

And in a footnote on the same page he acknowledges:

Unlocking this capability will require a new kind of training, for it to learn these extra skills.

Not trivial or baked-in to current AI progress, I think? Maybe I'm misunderstanding something.

As far as for enabling full computer access - yeah multi-modal models should allow this within a few years, but it remains of limited benefit if the working memory problem isn't solved.

EDIT 12/22/24: Well, it seems Leopold knew more than I did and just couldn't talk about it. We still don't have all the details on o3, but it really does seem like "more inference time compute" can be leveraged into reasoning capability.

1. ^{^}

   Page 9 of the PDF.

2. ^{^}

   Pages 34-37 of the PDF.

3. ^{^}

   Page 36 of the PDF.

Just skimmed the pdf. This is my first exposure to Aschenbrenner beyond "fired by OpenAI". I haven't listened to his interview with Dwarkesh yet. 

For some reason, the pdf reminds me a lot of Drexler's Engines of Creation. Of course, that was a book which argued that nanotechnology would transform everything, but which posed great perils, and shared a few ideas on how to counter those perils. Along the way it mentions that nanotechnology will lead to a great concentration of power, dubbed "the leading force", and says that the "cooperating democracies" of the world are the leading force for now, and can stay that way. 

Aschenbrenner's opus is like an accelerated version of this that focuses on AI. For Drexler. nanotechnology was still decades away. For Aschenbrenner, superintelligence is coming later this decade, and the 2030s will see a speedrun through the possibilities of science and technology, culminating in a year of chaos in which the political character of the world will be decided (since superintelligent AI will be harnessed by some political system or other). Aschenbrenner's take is that liberal democracy needs to prevail, it can do so if the US maintains its existing lead in AI, but to do so, it has to treat frontier algorithms as the top national security issue, and nationalize AI in some way or other. 

At first read, Aschenbrenner's reasoning seems logical to me in many areas. For example, I think AI nationalization is the logical thing for the US to do, given the context he describes; though I wonder if the US has enough institutional coherence to do something so forceful. (Perhaps it is more consistent with Trump's autocratic style, than with Biden's spokesperson-for-the-system demeanour.) Though the Harris brothers recently assured Joe Rogan that, as smart as Silicon Valley's best are, there are people like that scattered throughout the US government too; the hypercompetent people that @trevor [LW · GW] has talked about. 

When Aschenbrenner said that by the end of the 2020s, there will be massive growth in electrical production (for the sake of training AIs), that made be a bit skeptical. I believe superintelligence can probably design and mass-produce transformative material technologies quickly, but I'm not sure I believe in the human economy's ability to do so. However, I haven't checked the numbers, this is just a feeling (a "vibe"?). 

I become more skeptical when Aschenbrenner says there will be millions of superintelligent agents in the world - and the political future will still be at stake. I think, once you reach that situation, humanity exists at their mercy, not vice versa... Aschenbrenner also says he's optimistic about the solvability of superalignment; which I guess makes Anthropic important, since they're now the only leading AI company that's working on it. 

As a person, Aschenbrenner seems quite impressive (what is he, 25?). Apparently there is, or was, a post on Threads beginning like this: 

I feel slightly bad for AI's latest main character, Leopold Aschenbrenner. He seems like a bright young man, which is awesome! But there are some things you can only learn with age. There are no shortcuts

I can't find the full text or original post (but I am not on Threads). It's probably just someone being a generic killjoy - "things don't turn out how you expect, kid" - but I would be interested to know the full comment, just in case it contains something important. 

I am also on the hawkish side, and my projections of the future have a fair amount in common with Leopold's. Our recommendations for what to do are very different however. I am on team 'don't build and deploy AGI' rather than on team 'build AGI'. I don't think racing to AGI ensures the safety of liberal democracy, I believe it results in humanity's destruction. I think that even if we had AGI today, we wouldn't be able to trust it enough to use it safely without a lot more alignment work. If we trust it too much, we all die. If we don't trust it, it is not very useful as a tool to help us. Ryan and Buck's AI control theory helps somewhat with being able to use an untrustworthy AI, but that supposes that the creators will be wise enough to adhere to the careful control plan. I don't trust that they will. I think they'll screw up and unleash a demon.

There is a different path available. Seeking an international treaty. Establishing strong enforcement mechanisms, including inspections and constant monitoring of all datacenters and bio labs everywhere in the world. To ensure the safety of humanity we must prevent the development of bioweapons and also prevent the rise of rogue AGI.

If we can't come to such an arrangement peacefully with all the nations of the world, we must prepare for war. If we fail to enforce the worldwide halt on AI and bio weapons, we all die.

But I don't think that preparing for war should include racing for AGI. That is a major point where Leopold and I differ in recommendation for current and future action.

It's literally the worst possible message ever. 

1. AGI is awesome!
2. Free World Uber Alles Must Prevail
3. So, US government should race to AGI