I think this may be proving Raemon's point that there are a wide range of concepts. I consider the lower amount of alignment connotation of independence gaining a feature, not a bug, since we can say things like ethical independence gaining AGI or aligned independence gaining AGI without it sounding like an oxymoron. Also, I am not sure superintelligence is required to gain independence, since it may be possible to just think longer than a human to gain independence without thinking faster. That said, if out-of-control superintelligence is the right concept you are trying to get across, then use that.
Overwhelming superintelligence sounds like a useful term. A term I started using is independence gaining artificial general intelligence as the threshold for when we need to start being concerned about the AGI's alignment. An AI program that is sufficiently intelligent to be able to gain independence, such as by creating a self-replicating computer capable of obtaining energy and other things needed to achieve goals without any further assistance from humans.
For example, an independence gaining AGI connected to today's internet might complete intellectual tasks for money and then use the money to mail order printed circuit boards and other hardware. An independence gaining AGI with access to 1800s level technology might mine coal and build a steam engine to power a Babbage-like computer and then bootstrap to faster computing elements. An independence gaining AGI on Earth's moon might be able to produce solar panels and CPUs from the elements in the moon's crust, and produce an electromagnetic rail to launch probes off the moon. Of course, how smart the AGI has to be to gain independence is a function of what kind of hardware the AGI can get access to. An overwhelming superintelligence might be able to take over the planet with just access to a hardware random number generator and a high precision timer, but a computer controlling a factory could probably be less intelligent and still be able to gain independence.
One of the reasons I started using the term is because human level AGI is vague, and we don't know if we should be concerned by a human level AGI. Also, to determine if something is human level, we need to specify human level in what? 1950s computers were superhuman at arithmetic, but not chess, so is a 1950s computer human level or not? It may be hard to determine of a given computer + software is capable of gaining independence, but it is a more exact definition than just human level AGI.
Hm, I don't think I want the Human-Descended Ideal Agent and the AI-Descended Ideal Agent to be in complete agreement. I want them to be compatible, as in able to live in the same universe. I want the AI to not make humans go extinct, and be ethical in a way that the AI can explain to me and (in a non-manipulative way) convince me is ethical. But in some sense, I hope that AI can come up with something better than just what humans would want in a CEV way. (And what about the opinion of the other vertebrates and cephalopods on this planet, and the small furry creatures from Alpha Centauri?)
I don't think it is okay to do unethical things for music, music is not that important, but I hope that the AIs are doing some things that are as incomprehensible and pointless to us as music would be to evolution (or a being that was purely maximizing genetic fitness).
As a slightly different point, I think that the Ideal Agent is somewhat path dependent, and I think there are multiple different Ideal Agents that I would consider ethical and I would be happy to share the same galaxy with.
My P(doom) is 100% - Ɛ to Ɛ: 100% - Ɛ, Humanity has already destroyed the solar system (and the AGI is rapidly expanding to the rest of the galaxy) on at least some of the quantum branches due to an independence gaining AGI accident. I am fairly certain this was possible by 2010, and possibly as soon as around 1985. Ɛ, at least some of the quantum branches where independence gaining AGI happens will have a sufficiently benign AGI that we survive the experience or we will actually restrict computers enough to stop accidentally creating AGI. It is worth noting that if AGI has a very high probability of killing people, what it looks like in a world with quantum branching is periodically there will be AI winters when computers and techniques approach being capable of AGI, because many of the "successful" uses of AI result in deadly AGI, and so we just don't live long enough to observe those.
And if I am just talking with an average person, I say > 1%, and make the side comment that if a passenger plane had a 1% probability of crashing in the next flight, it would not take off.
Edit: And to really explain this would take a lot longer post, so I apologize for that. That said, if I had to choose, to prevent accidental AGI, I would be willing to restrict myself and everyone else to computers on the order of 512 KiB of RAM, 2 MiB of disk space as part of a comprehensive program to prevent existential risk.
Thank you for this, I still read it periodically.
1First of all, I do agree with you that why haven't other civilizations created AGIs that have then spread far enough to reach Earth is a really interesting question as well, and I would be happy to see a discussion on that question.
For that question, I think you are missing a fourth possibility, AGI is almost always deadly, so on quantum branches where it develops anywhere in the light cone, no one observes it (at least not for long). So we don't see other civilization's AGI because we just are not alive on those quantum branches.
At least to me Claude 4.5 definitely reminds me of the description of Agent-1 in ai-2027 for Early 2026: "On the other hand, Agent-1 is bad at even simple long-horizon tasks, like beating video games it hasn’t played before. Still, the common workday is eight hours, and a day’s work can usually be separated into smaller chunks; you could think of Agent-1 as a scatterbrained employee who thrives under careful management. Savvy people find ways to automate routine parts of their jobs."