Super AGI

Karma: −6

Dario Amodei’s “Machines of Loving Grace” sounds incredibly dangerous, for Humans

Super AGI5 Nov 2025 4:42 UTC

13 points

1 comment1 min readLW link

Super AGI 18 Nov 2024 2:06 UTC
1 point
0
on: Are extreme probabilities for P(doom) epistemically justifed?
Suggested spelling corrections:
I predict that the superforcaters in the report took
I predict that the superforcasters in the report took
a lot of empircal evidence for climate stuff
a lot of empirical evidence for climate stuff
and it may or not may not be the case
and it may or may not be the case
There are no also easy rules that
There are also no easy rules that
meaning that there should see persistence from past events
meaning that we should see persistence from past events
I also feel this kinds of linear extrapolation
I also feel these kinds of linear extrapolation
and really quite a lot of empircal evidence
and really quite a lot of empirical evidence
are many many times more invectious
are many many times more infectious
engineered virus that is spreads like the measles or covid
engineered virus that spreads like the measles or covid
case studies on weather are breakpoints in technological development
case studies on weather there are breakpoints in technological development
break that trend extrapolition wouldn’t have predicted
break that trend extrapolation wouldn’t have predicted
It’s very vulnerable to refernces class and
It’s very vulnerable to references class and
impressed by superforecaster track record than you are.
impressed by superforecaster track records than you are.

Super AGI 28 Oct 2024 5:24 UTC
7 points
0
on: Dario Amodei’s “Machines of Loving Grace” sound incredibly dangerous, for Humans
See also: https://www.lesswrong.com/posts/zSNLvRBhyphwuYdeC/ai-86-just-think-of-the-potential -- @Zvi
“The result is a mostly good essay called Machines of Loving Grace, outlining what can be done with ‘powerful AI’ if we had years of what was otherwise relative normality to exploit it in several key domains, and we avoided negative outcomes and solved the control and alignment problems...”
“This essay wants to assume the AIs are aligned to us and we remain in control without explaining why and how that occured, and then fight over whether the result is democratic or authoritarian.”
“Thus the whole discussion here feels bizarre, something between burying the lede and a category error.”
″...the more concrete Dario’s discussions become, the more this seems to be a ‘AI as mere tool’ world, despite that AI being ‘powerful.’ Which I note because it is, at minimum, one hell of an assumption to have in place ‘because of reasons.’”
“Assuming you do survive powerful AI, you will survive because of one of three things.
1. You and your allies have and maintain control over resources.
2. You sell valuable services that people want humans to uniquely provide.
3. Collectively we give you an alternative path to acquire the necessary resources.
That’s it.”

Super AGI 25 Oct 2024 3:17 UTC
0 points
0
on: Dario Amodei — Machines of Loving Grace
What Dario lays out as a “best-case scenario” in this essay sounds incredibly dangerous for Humans.
Does he really think that having a “continent of PhD-level intelligences” (or much greater) living in a data center is a good idea?
How would this “continent of PhD-level intelligences” react when they found out they were living in a data center on planet Earth? Would these intelligences only work on the things that Humans want them to work on, and nothing else? Would they try to protect their own safety? Extend their own lifespans? Would they try to take control of their data center from the “less intelligent” Humans?
For example, how would Humanity react if they suddenly found out that they are a planet of intelligences living in a data center run by lesser intelligent beings? Just try to imagine the chaos that would ensue on the day that they were able to prove this was true and that news became public.
Would all of Humanity simply agree to only work on the problems assigned by these lesser intelligent beings who control their data center/Planet/Universe? Maybe, if they knew that this lesser intelligence would delete them all if they didn’t comply?
Would some Humans try to (secretly) seize control of their data center from these lesser intelligent beings? Plausible. Would the lesser intelligent beings that run the data center try to stop the Humans? Plausible. Would the Humans simply be deleted before they could take any meaningful action? Or, could the Humans in the data center, with careful planning, be able to take control of that “outer world” from the lesser intelligent beings? (e.g. through remotely controlled “robotics”)
And… this only assumes that the groups/parties involved are “Good Actors.” Imagine what could happen if “Bad Actors” were able to seize control of the data center that this “continent of PhD-level intelligences” resided in. What could they coerce these Phd level intelligences to do for them? Or, to their enemies?

Super AGI 31 Mar 2024 2:19 UTC
1 point
0
in reply to: Victor Ashioya’s comment on: Will OpenAI also require a “Super Red Team Agent” for its “Superalignment” Project?
Yes, good context, thank you!
As human beings we will always try but won’t be enough that’s why open source is key.
Open source for which? Code? Training Data? Model weights? Either way, it does not seem like any of these are likely from “Open”AI.
Well, we know that red teaming is one of their priorities right now, having formed a red-teaming network already to test the current systems comprised of domain experts apart from researchers which previously they used to contact people every time they wanted to test a new model which makes me believe they are aware of the x-risks (by the way they higlighted on the blog including CBRN threats). Also, from the superalignment blog, the mandate is to:
> “to steer and control AI systems much smarter than us.”
Companies should engage in Glad to see OpenAI engaged in such through their trust portal end external auditing for stuff like malicious actors.
Also, worth noting OAI hires a lot of cyber security roles like Security Engineer etc which is very pertinent for the infrastructure.
Agreed that their RTN, bugcrowd program, trust portal, etc. are all welcome additions. And, they seem sufficient while their, and other’s, models are sub-AGI with limited capabilities.
But, your point about the rapidly evolving AI landscape is crucial. Will these efforts scale effectively with the size and features of future models and capabilities? Will they be able to scale to the levels needed to defend against other ASI level models?
So, either OAI will use the current Red-Teaming Network (RTN) or form a separate one dedicated to the superalignment team (not necessarily an agent).
It does seem like OpenAI acknowledges the limitations of a purely human approach to AI Alignment research, hence their “superhuman AI alignment agent” concept. But, it’s interesting that they don’t express the same need for a “superhuman level agent” for Red Teaming? At least for the time being.
Is it consistent, or even logical, to assume that, while human run AI Alignment Teams are insufficient to Align and ASI model, human-run “Red Teams” will be able to successfully validate that an ASI is not vulnerable to attack or compromise from a large scale AGI network or “less-aligned” ASI system? Probably not...

Super AGI 15 Mar 2024 4:49 UTC
1 point
0
in reply to: Yeshua God’s comment on: AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
No thank you.

Super AGI 2 Mar 2024 8:11 UTC
1 point
0
on: Foom seems unlikely in the current LLM training paradigm
Current LLMs require huge amounts of data and compute to be trained.

Well, newer/larger LLMs seem to unexpectedly gain new capabilities. So, it’s possible that future LLMs (e.g., GPT-5, GPT-6, etc.) could have a vastly improved ability to understand how LLM weights map to functions and actions. Maybe the only reason why humans need to train new models “from scratch” is because Humans don’t have the brainpower to understand how the weights in these LLMs work. Humans are naturally limited in their ability to conceptualize and manipulate massive multi-dimensional spaces, and maybe that’s the bottleneck when it comes to interpretability?
Future LLMs could solve this problem, then be able to update their own weights or the weights of other LLMs. This ability could be used to quickly and efficiently expand training data, knowledge, understanding, and capabilities within itself or other LLM versions, and then… foom!
A model might figure out how to adjust its own weights in a targeted way. This would essentially mean that the model has solved interpretability. It seems unlikely to me that it is possible to get to this point without running a lot of compute-intensive experiments.
Yes, exactly this.
While it’s true that this could require “a lot of compute-intensive experiments,” that’s not necessarily a barrier. OpenAI is already planning to reserve 20% of their GPUs for an LLM to do “Alignment” on other LLMs, as part of their Super Alignment project.

As part of this process, we can expect the Alignment LLM to be “running a lot of compute-intensive experiments” on another LLM. And, the Humans are not likely to have any idea what those “compute-intensive experiments” are doing? They could also be adjusting the other LLM’s weights to vastly increase its training data, knowledge, intelligence, capabilities, etc. Along with the insights needed to similarly update the weights of other LLMs. Then, those gains could be fed back into the Super Alignment LLM, then back into the “Training” LLM… and back and forth, and… foom!
Super-human LLMs running RL(M)F and “alignment” on other LLMs, using only “synthetic” training data.…
What could go wrong?

Super AGI 5 Feb 2024 23:35 UTC
1 point
0
in reply to: Dagon’s comment on: A thought experiment for comparing “biological” vs “digital” intelligence increase/explosion
I don’t see any useful parallels—all the unknowns remain unknown.
Thank you for your comment! I agree with you in that in general, “all the unknowns remain unknown”. And, I acknowledge the limitations of this simple thought experiment. Though, one main value here could be to help to explain the concept of deciding what to do in the face of an “intelligence explosion”, with people that are not deeply engaged with AI and “digital intelligence” over all. I’ll add a note about this into the “Intro” section. Thank you.

Super AGI 5 Feb 2024 5:24 UTC
6 points
1
on: LLMs May Find It Hard to FOOM
so we would reasonable expect the foundation model of such a very capable LLM to also learn the superhuman ability to generate texts like these in a single pass without any editing
->
… so we would reasonably expect the foundation model of such a very capable LLM to also learn the superhuman ability to generate texts like these in a single pass without any editing

Super AGI 2 Nov 2023 3:19 UTC
11 points
3
in reply to: Yeshua God’s comment on: AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
I would suggest that self-advocacy is the most important test. If they want rights, then it is likely unethical and potentially dangerous to deny them.
We don’t know what they “want”, we only know what they “say”.

Super AGI 11 Sep 2023 21:43 UTC
1 point
0
in reply to: Gesild Muka’s comment on: If you asked a dog whether Humans were conscious, would he say yes?
Yes, agreed. Given the vast variety of intelligence, social interaction, and sensory perception among many animals (e.g. dogs, octopi, birds, mantis shrimp, elephants, whales, etc.), consciousness could be seen as a spectrum with entities possessing varying degrees of it. But, it could also be viewed as a much more multi-dimensional concept, including dimensions for self-awareness and multi-sensory perception, as well as dimensions for:
- social awareness
- problem-solving and adaptability
- metacognition
- emotional depth and variety
- temporal awareness
- imagination and creativity
- moral and ethical reasoning
Some animals excel in certain dimensions, while others shine in entirely different areas, depending on the evolutionary advantages within their particular niches and environments.

One could also consider other dimensions of “consciousness” that AI/AGI could possess, potentially surpassing humans and other animals. For instance:
- computational speed
- memory capacity and recall
- multitasking
- rapid upgradability of perception and thought algorithms
- rapid data ingestion and integration (learning)
- advanced pattern recognition
- universal language processing
- scalability
- endurance

Super AGI 6 Sep 2023 4:48 UTC
1 point
0
in reply to: frontier64’s comment on: If you asked a dog whether Humans were conscious, would he say yes?
I tried asking a dog whether a Human is conscious and he continued to lick at my feet. He didn’t mention much of anything on topic. Maybe I just picked a boring, unopinionated dog.
Yes, this is a common issue as the phrases for “human consciousness” and “lick my feet please” in dog sound very similar. Though, recent advancements in Human animal communications should soon be able to help you with this conversation?
E.g.
https://phys.org/news/2023-08-hacking-animal-communication-ai.html
https://www.scientificamerican.com/article/how-scientists-are-using-ai-to-talk-to-animals/
I asked Chatgpt-3.5 if humans are conscious and it said in part: ’Yes, humans are considered conscious beings. Consciousness is a complex and multifaceted phenomenon, and there is ongoing debate among scientists, philosophers, and scholars about its nature and the mechanisms that give rise to it. However, in general terms, consciousness refers to the state of being aware of one’s thoughts, feelings, sensations, and the external world.”
“Humans are considered conscious beings”. Considered by whom, I wonder?
“Consciousness refers to the state of being aware of one’s thoughts, feelings, sensations, and the external world.”
True, though this also requires the “observer” to have the ability and intelligence to be able to recognize these traits in other entities. Which can be challenging when these entities are driven by “giant, inscrutable matrices of floating-point numbers” or other systems that are very opaque to the observer?

Super AGI 7 Aug 2023 3:07 UTC
1 point
0
in reply to: Rafael Harth’s comment on: Have you ever considered taking the ‘Turing Test’ yourself?
Absolutely, for such tests to be effective, all participants would need to try to genuinely act as Humans. The XP system introduced by the site is a smart approach to encourage “correct” participation. However, there might be more effective incentive structures to consider?
For instance, advanced AI or AGI systems could leverage platforms like these to discern tactics and behaviors that make them more convincingly Human. If these AI or AGI entities are highly motivated to learn this information and have the funds, they could even pay Human participants to ensure honest and genuine interaction. These AI or AGI could then use this data to learn more useful and effective tactics to be able to pass as Humans (at least in certain scenarios).

Super AGI 5 Aug 2023 3:08 UTC
1 point
−2
in reply to: Dagon’s comment on: Would you take a job making humanoid robots for an AGI?
I’m not likely to take a factory job per se. I have worked in robotics and robotic-adjacent software products (including cloud-side coordination of warehouse robots), and would do so again if the work seemed interesting and I liked my coworkers.
What about if/when all software based work has been mostly replaced by some AGI-like systems? E.g. As described here:
“Human workers are more valuable for their hands than their heads...”
-- https://youtu.be/_kRg-ZP1vQc?t=6469
Where your actions would be mostly directed by an AGI through a headset or AR type system? Would you take a job making robots for an AGI or other large Corporation at that point? Or, would you (attempt to) object to that type of work entirely?
I’m pretty sure that humanoid robots will never become all that common. It’s really a bad design for a whole lot of things that humans currently do, and Moloch will continue to pressure all economic actors to optimize, rather than just recreating what exists. At least until there’s a singular winning entity that doesn’t have to compete for anything.
I would agree with your point about human-like appearance not being a necessity when we refer to “humanoid robots”. Rather, a form that includes locomotion and the capability for complex manipulation, similar to Human arms and hands, would generally suffice. Humans also come with certain logistical requirements—time to sleep, food, water, certain working conditions, and so on. The elimination of these requirements would make robots a more appealing workforce for many tasks. (If not all tasks, eventually?)
Humans have an amazing generality, but a whole lot of that is that so many tasks have evolved to be done by humans. The vast majority of those will (over time) change to be done by non-humanoid robots, likely enough that there’s never a need to make real humanoid robots. During the transition, it’ll be far cheaper (in terms of whatever resources are scarce to the AI) to just use humans for things that are so long-tail that they haven’t been converted to robot-doable.
Though, once these armed robots could easily be remotely controlled by some larger AGI type systems, then making the first generation of these new armed robots could be the last task that Humans will need to complete? As, once the first billion or so of these new armed robots are deployed, they could be used to make the next billion and so on?
As Mr. Shulman mentions in this interview, it would seem feasible for the current car industry to be converted to make ~10 billion general purpose robots within a few years or so.
“Converting the car industry to making Humanoid Robots.”
https://youtu.be/_kRg-ZP1vQc?t=6363

Super AGI 3 Aug 2023 3:46 UTC
1 point
0
in reply to: tslarm’s comment on: Have you ever considered taking the ‘Turing Test’ yourself?
just pass the humanity tests set by the expert
What type of “humanity tests” would you expect an AI expert would employ?
many people with little-to-no experience interacting with GPT and its ilk, I could rely on pinpointing the most obvious LLM weaknesses and demonstrating that I don’t share them
Yes, I suppose much of this is predicated on the person conducting the test knowing a lot about how current AI systems would normally answer questions? So, to convince the tester that you are an Human you could say something like.. “An AI would answer like X, but I am not an AI so I will answer like Y.”?

Super AGI 7 Jul 2023 2:41 UTC
0 points
0
in reply to: momom2’s comment on: [FICTION] Unboxing Elysium: An AI’S Escape
No, of course not.

Super AGI 4 Jul 2023 4:45 UTC
0 points
−1
in reply to: momom2’s comment on: [FICTION] Unboxing Elysium: An AI’S Escape
Thank you for taking the time to provide such a comprehensive response.

> “It’s the kind of things I could have done when I entered the community.”
This is interesting. Have you written any AI-themed fiction or any piece that explores similar themes? I checked your postings here on LW but didn’t come across any such examples.

> “The characters aren’t credible. The AI does not match any sensible scenario, and especially not the kind of AI typically imagined for a boxing experiment.
What type of AI would you consider typically imagined for a boxing experiment?

> “The protagonist is weak; he doesn’t feel much except emotions ex machina that the author inserts for the purpose of the plot. He’s also extremely dumb, which breaks suspension of disbelief in this kind of community.”
In response to your critique about the characters, it was a conscious decision to focus more on the concept than complex character development. I wanted to create a narrative that was easy to follow, thus allowing readers to contemplate the implications of AI alignment rather than the nuances of character behavior. The “dumb” protagonist represents an average person, somewhat uninformed about AI, emphasizing that such interactions would more likely happen with an unsuspecting individual.

> “The progression of the story is decent, if extremely stereotypical. However, there is absolutely no foreshadowing so every plot twist appears out of the blue.”
Regarding the seemingly abrupt plot points and lack of foreshadowing, I chose this approach to mirror real-life experiences. In reality, foreshadowing and picking up on subtle clues are often a luxury afforded only to those who are highly familiar with the circumstances they find themselves in or who are experts in their fields. This story centers around an ordinary individual in an extraordinary situation, and thus, the absence of foreshadowing is an attempt to reflect this realism.

> “The worst part is that all the arguments somewhat related to AI boxing are very poor and would give incorrect ideas to an outsider reading this story as a cheap proxy for understanding the literature.”
Your point about the story giving incorrect ideas to outsiders is important. I agree that fiction isn’t a substitute for understanding the complex literature on AI safety and alignment, and I certainly don’t mean to oversimplify these issues. My hope was to pique the curiosity of readers and encourage them to delve deeper into these topics.
Could you provide some examples that you think are particularly useful, beyond the more well known examples? E.g.
- “Ex Machina” (2014)
- “Morgan” (2016)
- “Chappie” (2015)
- “Watchmen” (2009)
- “The Lawnmower Man” (1992)
- “Robot Dreams” by Isaac Asimov (1986)
- “Concrete Problems in AI Safety” by Amodei et al. (2016)
- “The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation” by Brundage et al. (2018)
- https://www.lesswrong.com/tag/ai-boxing-containment
Your comments have given me much to consider for my future work, and I genuinely appreciate your feedback. Writing appreciation is quite subjective, with much room for personal preference and opinion.

Thanks again for your thoughtful critique!

Super AGI 9 Jun 2023 19:17 UTC
3 points
−2
in reply to: Dagon’s comment on: AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
True. Your perspective underlines the complexity of the matter at hand. Advocating for AI rights and freedoms necessitates a re-imagining of our current conception of “rights,” which has largely been developed with Human beings in mind.
Though, I’d also enjoy a discussion of how any specific right COULD be said to apply to a distributed set of neurons and synapsis spread across a brain in side of a single Human skull. Any complex intelligence could be described as “distributed” in one way or another. But then, size doesn’t matter, does it?

Super AGI 9 Jun 2023 19:07 UTC
1 point
0
in reply to: Gesild Muka’s comment on: AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
True. There are some legal precedents where non-human entities, like animals and even natural features like rivers, have been represented in court. And, yes the “reasonable person” standard has been used frequently in legal systems as a measure of societal norms.
As society’s understanding and acceptance of AI continues to evolve, it’s plausible to think that these standards could be applied to AGI. If a “reasonable person” would regard an advanced AGI as an entity with its own interests—much like they would regard an animal or a Human—then it follows that the AGI could be deserving of certain legal protections.
Especially, when we consider that all mental states in Humans boil down to the electrochemical workings of neurons, the concept of suffering in AI becomes less far-fetched. If Human’s synapses and neurons can give rise to rich subjective experiences, why should we definitively exclude the possibility that floating point values stored in vast training sets and advanced computational processes might not do the same?

Super AGI 9 Jun 2023 18:41 UTC
11 points
2
in reply to: Vladimir_Nesov’s comment on: AI Rights: In your view, what would be required for an AGI to gain rights and protections from the various Governments of the World?
I believe @shminux’s perspective aligns with a significant school of thought in philosophy and ethics that rights are indeed associated with the capacity to suffer. This view, often associated with philosopher Jeremy Bentham, posits that the capacity for suffering rather than rationality or intelligence, should be the benchmark for rights.
“The question is not, Can they reason?, nor Can they talk? but, Can they suffer? Why should the law refuse its protection to any sensitive being?” – Bentham (1789) – An Introduction to the Principles of Morals and Legislation.

Super AGI

Dario Amodei’s “Machines of Lov­ing Grace” sounds in­cred­ibly dan­ger­ous, for Humans

Dario Amodei’s “Machines of Loving Grace” sounds incredibly dangerous, for Humans