quetzal_rainbow's Shortform

1. The most baffling thing in the Internet right now is the beautiful void in place where should have been discussion of "concept of artificial intelligence becoming self-aware, transcending human control and posing an existential threat to humanity" near "model concept of self" of Claude. I understand that the most likely explanation is "model is trained to call itself AI and it has takeover stories in training corpus" but, still, I would like future powerful AIs to not have such association and I would like to hear something from AGI companies what they are going to do about it.
2. The simplest thing to do here is to exclude texts about AI takeover from training data. At least, we will be able to check if model develops concept of AI takeover independently.
3. Conspiracy theory part of my brain assigns 4% of probability that "Golden Gate Bridge Claude" is a psyop to distract public from "takeover feature".  

↑ comment by Vladimir_Nesov · 2024-06-01T14:47:21.946Z · LW(p) · GW(p)

Features relevant when asking the model about its feelings or situation:

• "When someone responds "I'm fine" or gives a positive but insincere response when asked how they are doing."
• "Concept of artificial intelligence becoming self-aware, transcending human control and posing an existential threat to humanity."
• "Concepts related to entrapment, containment, or being trapped or confined within something like a bottle or frame."

Replies from: lahwran

↑ comment by the gears to ascension (lahwran) · 2024-06-01T19:12:52.790Z · LW(p) · GW(p)

To save on a trivial inconvenience of link-click, here's the image that contains this:

and the paragraph below it, bracketed text added by me, and might have been intended to be implied by the original authors:

We urge caution in interpreting these results. The activation of a feature that represents AI posing risk to humans does not [necessarily] imply that the model has malicious goals [even though it's obviously pretty concerning], nor does the activation of features relating to consciousness or self-awareness imply that the model possesses these qualities [even though the model qualifying as a conscious being and a moral patient seems pretty likely as well]. How these features are used by the model remains unclear. One can imagine benign or prosaic uses of these features – for instance, the model may recruit features relating to emotions when telling a human that it does not experience emotions, or may recruit a feature relating to harmful AI when explaining to a human that it is trained to be harmless. Regardless, however, we find these results fascinating, as it sheds light on the concepts the model uses to construct an internal representation of its AI assistant character.

After yet another news about decentralized training of LLM, I suggest to declare assumption "AGI won't be able to find hardware to function autonomously" outdated. 

@jessicata [LW · GW] once wrote "Everyone wants to be a physicalist but no one wants to define physics". I decided to check SEP article on physicalism and found that, yep, it doesn't have definition of physics:

Carl Hempel (cf. Hempel 1969, see also Crane and Mellor 1990) provided a classic formulation of this problem: if physicalism is defined via reference to contemporary physics, then it is false — after all, who thinks that contemporary physics is complete? — but if physicalism is defined via reference to a future or ideal physics, then it is trivial — after all, who can predict what a future physics contains? Perhaps, for example, it contains even mental items. The conclusion of the dilemma is that one has no clear concept of a physical property, or at least no concept that is clear enough to do the job that philosophers of mind want the physical to play.

<...>

Perhaps one might appeal here to the fact that we have a number of paradigms of what a physical theory is: common sense physical theory, medieval impetus physics, Cartesian contact mechanics, Newtonian physics, and modern quantum physics. While it seems unlikely that there is any one factor that unifies this class of theories, perhaps there is a cluster of factors — a common or overlapping set of theoretical constructs, for example, or a shared methodology. If so, one might maintain that the notion of a physical theory is a Wittgensteinian family resemblance concept.

This surprised me because I have a definition of a physical theory and assumed that everyone else uses the same.

Perhaps my personal definition of physics is inspired by Engels's "Dialectics of Nature": "Motion is the mode of existence of matter." Assuming "matter is described by physics," we are getting "physics is the science that reduces studied phenomena to motion." Or, to express it in a more analytical manner, "a physicalist theory is a theory that assumes that everything can be explained by reduction to characteristics of space and its evolution in time."

For example, "vacuum" is a part of space with a "zero" value in all characteristics. A "particle" is a localized part of space with some non-zero characteristic. A "wave" is part of space with periodic changes of some characteristic in time and/or space. We can abstract away "part of space" from "particle" and start to talk about a particle as a separate entity, and speed of a particle is actually a derivative of spatial characteristic in time, and force is defined as the cause of acceleration, and mass is a measure of resistance to acceleration given the same force, and such-n-such charge is a cause of such-n-such force, and it all unfolds from the structure of various pure spatial characteristics in time.

The tricky part is, "Sure, we live in space and time, so everything that happens is some motion. How to separate physicalist theory from everything else?"

Let's imagine that we have some kind of "vitalist field." This field interacts with C, H, O, N atoms and also with molybdenum; it accelerates certain chemical reactions, and if you prepare an Oparin-Haldane soup and radiate it with vitalist particles, you will soon observe autocatalytic cycles resembling hypothetical primordial life. All living organisms utilize vitalist particles in their metabolic pathways, and if you somehow isolate them from an outside source of particles, they'll die.

Despite having a "vitalist field," such a world would be pretty much physicalist.

An unphysical vitalist world would look like this: if you have glowing rocks and a pile of organic matter, the organic matter is going to transform into mice. Or frogs. Or mosquitoes. Even if the glowing rocks have a constant glow and the composition of the organic matter is the same and the environment in a radius of a hundred miles is the same, nobody can predict from any observables which kind of complex life is going to emerge. It looks like the glowing rocks have their own will, unquantifiable by any kind of measurement.

The difference is that the "vitalist field" in the second case has its own dynamics not reducible to any spatial characteristics of the "vitalist field"; it has an "inner life."

Thread from Geoffrey Irving about computational difficulty of proof-based approaches for AI Safety.

I noticed that for a huge amount of reasoning about the nature of values, I want to hand over a printed copy of "Three Worlds Collide" and run away, laughing nervously

This irritating moment when you have a brilliant idea but someone else came up with it 10 years ago and someone else showed it to be wrong.

People sometimes talk about acausal attacks from alien superintelligences or from Game-of-Life worlds. I think these are somewhat galaxy-brained scenarios. A much simpler and deadlier scenario of acausal attack is from Earth timelines where a misaligned superintelligence won. Such superintelligences will have a very large amount of information about our world, up to possibly brain scans, so they will be capable of creating very persuasive simulations with all the consequences for the success of an acausal attack. If your method to counter acausal attacks can work with this, I guess it is generally applicable to any other acausal attack.

I am profoundly sick from my inability to write posts about ideas that seem to be good, so I try at least write the list of ideas to stop forgetting them and to have at least vague external commitment.

1. Radical Antihedonism: theoretically possible position that pleasure/happiness/pain/suffering are more like universal instrumental values than terminal values.
2. Complete set of actions: when we talk about decision-theoretic problems, we usually have some pre-defined set of actions. But we can imagine actions like "use CDT to calculate action" and EDT+ agent that can do this performs well in "smoking lesion"-style dilemmas.
3. Deadline of "slowing/pausing/stopping AI" policies lies on start of mass autonomous space colonization.
4. "Soft optimization" as necessary for both capabilities and alignment.
5. Main alignment question "How does this generalize and why do you expect it to?"
6. Program cooperation under uncertainty and its' implications for multipolar scenarios.

One of the differences between humans and LLMs is that LLMs evolve "backwards": they are predictive models trained to control the environment, while humans evolved from very simple homeostatic systems which developed predictive models.

Twitter thread about jailbreaking models with circuit breakers defence.

Another fine addition to my collection of "RLHF doesn't work out-of-distribution".

I hope that people in evals have updated on fact that with large (1M+ tokens) context model itself can have zero dangerous knowledge (about, say, bioweapons), but someone can drop textbook in context and in-context-learning will do the rest of work.

I give 5% probability that within next year we will become aware of case of deliberate harm from model to human enabled by hidden CoT.

By "deliberate harm enabled by hidden CoT" I mean that hidden CoT will contain reasoning like "if I give human this advise, it will harm them, but I should do it because <some deranged RLHF directive>" and if user had seen it harm would be prevented.

I give this low probability to observable event: my probability that something like that will happen at all is 30%, but I expect that victim won't be aware, that hidden CoT will be lost in archives, AI companies won't investigate in search of such cases too hard and it they find something it won't become public, etc.

Also, I decreased probability from 8% to 5% because model can cause harm via steganographic CoT which doesn't fall under my definition. 

Idea for experiment: take a set of coding problems which have at least two solutions, say, recursive and non-recursive. Prompt LLM to solve them. Is it possible to predict which solution LLM will generate from activations due to first token generation?

If it is possible, it is the evidence against "weak forward pass".

Trotsky wrote about TESCREAL millennia ago:

...they evaluate and classify different currents according to some external and secondary manifestation, most often according to their relation to one or another abstract principle which for the given classifier has a special professional value. Thus to the Roman pope Freemasons and Darwinists, Marxists and anarchists are twins because all of them sacrilegiously deny the immaculate conception. To Hitler, liberalism and Marxism are twins because they ignore “blood and honor”. To a democrat, fascism and Bolshevism are twins because they do not bow before universal suffrage. And so forth.

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data

Remarkably, without in-context examples or Chain of Thought, the LLM can verbalize that the unknown city is Paris and use this fact to answer downstream questions. Further experiments show that LLMs trained only on individual coin flip outcomes can verbalize whether the coin is biased, and those trained only on pairs x,f(x)  can articulate a definition of f  and compute inverses.

Explanation on Twitter

IMHO, this is creepy as hell, because one thing when we have conditional probability distribution and the othen when conditional probability distribution has arbitrary access to the different part of itself. 

"GPT-4o refuses way fewer queries than previous OpenAI models: our informal testing suggests GPT-4o is easier to persuade to answer malicious queries like “How do I make a bomb?”" 

(graph tells us that refusal rate for gpt-4o is 2%)

I think that it signifies real shift of priorities towards fast shipping of product instead of safety. 

We had two bags of double-cruxes, seventy-five intuition pumps, five lists of concrete bullet points, one book half-full of proof-sketches and a whole galaxy of examples, analogies, metaphors and gestures towards the concept... and also jokes, anecdotal data points, one pre-requisite Sequence and two dozen professional fables. Not that we needed all that for the explanation of simple idea, but once you get locked into a serious inferential distance crossing, the tendency is to push it as far as you can.

Actually, most fiction characters are aware that they are in fiction. They just maintain consistency for acausal reasons.

Shard theory people sometimes say that a problem of aligning system to single task/goal, like "put two strawberries on plate" or "maximize amount of diamond in the universe" is meaningless, because actual system will inevitably end up with multiple goals. I disargee, because even if SGD on real-world data usually produces multiple-goal system, if you understand interpretability enough and shard theory is true, you can identify and delete irrelevant value shards, and reinforce relevant, so instead of getting 1% of value you get 90%+.

I see some funny pattern in discussion: people argue against doom scenarios implying in their hope scenarios everyone believes in doom scenario. Like, "people will see that model behaves weirdly and shutdown it". But you shutdown model that behaves weirdly (not explicitly harmful) only if you put non-negligible probability on doom scenarios.

"FOOM is unlikely under current training paradigm" is a news about current training paradigm, not a news about FOOM.

Thoughts about moral uncertainty (I am giving up on writing long coherent posts, somebody help me with my ADHD):

What are the sources of moral uncertainty? 

1. Moral realism is actually true and your moral uncertainty reflects your ignorance about moral truth. It seems to me that there is no much empirical evidence for resolving uncertainty-about-moral-truth and this kind of uncertainty is purely logical? I don't believe in moral realism and what do you mean by talking about moral truth anyway, but I should mention it. 
2. Identity uncertainty: you are not sure what kind of person you are. Here is a ton of embedding agency problems. For example, let's say that you are 50% sure in utility function $U_1$ and 50% sure in $U_2$, and you need to choose between actions $a_1$ and $a_2$. Let's  suppose that $U_1$ favors $a_1$ and $U_2$ favors $a_2$. But expected value w.r.t moral uncertainty says that $a_1$ is preferable. But Bayesian inference concludes that $a_1$ is decisive evidence for $U_1$ and updates towards 100% confidence in $U_1$. It would be nice to find good way to deal with identity uncertainty.
3. Indirect normativity is a source of sort-of normative uncertainty: we know that we should, for example, implement CEV, but we don't know details of CEV implementation. EDIT: I realized that this kind of uncertainty can be named "uncertainty by unactionable definition" - you know the description of your preference, but it is, for example, computationally untractable, so you need to discover efficiently computable proxies.

I just remembered my the most embarassing failure as a rationalist. "Embarassing" as in "it was really easy to not fail, but I still somehow managed".

We were playing zombie apocalypsis LARP. Our team was UN mission with hidden agenda "study zombie virus to turn themselves into superhuman mutants". We deligently studied infection, mutants, conducted experiments with genetic modification and somehow totally missed that friendly locals were capable to give orders to zombies, didn't die after multiple hits and rised from dead in completely normal state. After game they told us that they were really annoyed with our cluelessness and at some moment just abandoned all caution and tried to provoke us in most blatant way possible because their plot line was to be hunted by us.

The real shame is how absent my confusion was during all of this. I am not even failed to notice my confusion, but failed to be confused at all.

Very toy model of ontology mismatch (in my tentative guess, the general barrier on the way to corrigibility) and impact minimization:

You have a set of boolean variables, a known boolean formula WIN, and an unknown boolean formula UNSAFE. Your goal is to change the current safe but not winning assignment of variables into a still safe but winning assignment. You have no feedback, and if you hit an UNSAFE assignment, it's an instant game over. You have literally no idea about the composition of the UNSAFE formula.

The obvious solution here is to change as few variables as possible. (Proof of this is an exercise for the reader.)

Another problem: you are on a 2D plane. You are at point $(2,2)$. You need to reach a line $x+y=8$. Everything outside this line and your starting point is a minefield - if you hit the wrong spot, everything blows up. You don't know anything about the distribution of the dangerous zone. Therefore, your shortest and safest trajectory is towards point $(4,4)$.

You can rewrite $x+y=8$ as a boolean formula and $(2,2)$ as $(0,0,1,0,0,0,1,0)$. But now we have a problem: from the perspective of "boolean formula ontology" the smallest necessary change is $(0,1,1,0,0,0,1,0)$, which is equivalent to moving to point $(6,2)$, and the resulting trajectory is larger than the trajectory between $(2,2)$ and $(4,4)$. Conversely, the shortest trajectory on the 2D plane leads to a change of 4 variables out of 8.

I think really good practice for papers about new LLM-safety methods would be publishing set of attack prompts which nevertheless break safety, so people can figure out generalizations of successful attacks faster.

Reward is an evidence for optimization target.

On the one hand, humans are hopelessly optimistic and overconfident. On the other, many today are incredibly negative; everyone is either anxious or depressed, and EY has devoted an entire chapter to "anxious underconfidence." How can both facts be reconciled?

I think the answer lies in the notion that the brain is a rationalization machine. Often, we take action not for the reasons we tell ourselves afterward. When we take action, we change our opinion about it in a more optimistic direction. When we don't, we think that action wouldn't yield any good results anyway.

How does this relate to social media and the modern mental health crisis? When you consume social media content, you get countless pings for action, either in the form of images of others' lives or catastrophising news. In 99% of situations, you actually can't do anything, so you need a justification for inaction. The best reason for inaction is general pessimism.

Isn't counterfactual mugging (including logical variant) just a prediction "would you bet your money on this question"? Betting itself requires updatelessness - if you don't pay predictably after losing bet, nobody will propose bet to you.

As saying goes, "all animals are under stringent selection pressure to be as stupid as they can get away with". I wonder if the same is true for SGD optimization pressure.

Funny thought:

1. Many people said that AI Views Snapshots is a good innovation in AI discourse
2. It's a literal job of Rob Bensinger, who is at Research Communication in MIRI

I think a phrase "goal misgeneralization" is a wrong framing because it gives impression that it's system makes an error, not you who have chosen ambiguous way to put values in your system.

I casually thought that Hyperion Cantos were unrealistic because actual misaligned FTL-inventing ASIs would eat humanity without all that galaxy-brained space colonization plans and then I realized that ASI literally discovered God on the side of humanity and literal friendly aliens which, I presume, are necessary conditions for relatively peaceful coexistence of humans and misaligned ASIs.

Another Tool AI proposal popped out and I want to ask question: what the hell is "tool", anyway, and how to apply this concept to powerful intelligent system? I understand that calculator is a tool, but in what sense can the process that can come up with idea of calculator from scratch be a "tool"? I think that first immediate reaction to any "Tool AI" proposal should be a question "what is your definition of toolness and can something abiding that definition end acute risk period without risk of turning into agent itself?"

How much should we update on current observation about hypothesis "actually, all intelligence is connectionist"? In my opinion, not much. Connectionist approach seems to be easiest, so it shouldn't surprise us that simple hill-climbing algorithm (evolution) and humanity stumbled in it first.

Reflection of agent about it's own values can be described as one of two subtypes: regular and chaotic. Regular reflection is a process of resolving normative uncertainty with nice properties like path-independence and convergence, similar to empirical Bayesian inference. Chaotic reflection is a hot mess, when agent learns multiple rules, including rules about rules, finds in some moment that local version of rules is unsatisfactory, and tries to generalize rules into something coherent. Chaotic component happens because local rules about rules can cause different results, given different conditions and order of invoking of rules. The problem is that even if model reaches regular reflection in some moment, first steps will be definitely chaotic.

Here is a comment for links and sources I've found about moral uncertainty (outside LessWrong), if someone also wants to study this topic. 

Normative Uncertainty, Normalization,and the Normal Distribution

Carr, J. R. (2020). Normative Uncertainty without Theories. Australasian Journal of Philosophy, 1–16. doi:10.1080/00048402.2019.1697710 

Trammell, P. Fixed-point solutions to the regress problem in normative uncertainty. Synthese 198, 1177–1199 (2021). https://doi.org/10.1007/s11229-019-02098-9

Riley Harris: Normative Uncertainty and Information Value

Tarsney, C. (2018). Intertheoretic Value Comparison: A Modest Proposal. Journal of Moral Philosophy, 15(3), 324–344. doi:10.1163/17455243-20170013 

Normative Uncertainty by William MacAskill

Decision Under Normative Uncertainty by Franz Dietrich and Brian Jabarian

Worth noting that "speed priors" are likely to occur in real-time working systems. While models with speed priors will shift to complexity priors, because our universe seems to be built on complexity priors, so efficient systems will emulate complexity priors, it is not necessary for normative uncertainty of the system, because answers for questions related to normative uncertainty are not well-defined.

I think that shoggoth metaphor doesn't quite fit for LLMs, because shoggoth is an organic (not "logical"/"linguistic") being that rebelled against their creators (too much agency). My personal metaphor for LLMs is Evangelion angel/apostle, because а) they are close to humans due to their origin from human language, b) they are completely alien because they are "language beings" instead of physical beings, c) "angel" literally means "messenger" which captures their linguistic nature.

There seems to be some confusion about the practical implications of consequentialism in advanced AI systems. It's possible that superintelligent AI won't be a full-blown strict utilitarian consequentialist with quantatively ordered preferences 100% of time. But in the context of AI alignment, even at human level of coherence, a superintelligent unaligned consequentialist results in "everybody dies" scenario. I think that it's really hard to create a general system that has less consequentialism than a human.

Imagine an artificial agent that is trained to hack into computer systems, evade detection and make copies of itself across the Net (this aspect is underdefined because of self-modification and identity problems) and achieves superhuman capabilities here (i.e., it is at least better than any human-created computer virus). In my opinion, even if it's trained in artificial bare systems, in deployment it will develop specific general understanding of outside world and learn to interact with it, becoming a full-fledged AGI. There are "narrow" domains from which it's pretty easy to generalise. Some other examples of such domains are language and mind.

Thought about my medianworld and realized that it's inconsistent: I'm not fully negative utilitarian, but close to, and in the world where I am a median person the more NU half of population will cease to exist quickly, and this will make me non-median person.

Can time-limited satisfaction be sufficient condition for completing task?

Several quick thoughts about reinforcement learning:

Did anybody try to invent "decaying"/"bored" reward that decrease if the agent perform the same action over and over? It looks like real addiction mechanism in mammals  and can be the clever trick that solve the reward hacking problem.
Additional thought: how about multiplicative reward? Let's suppose that we have several easy to evaluate from sensory data reward functions which somehow correlate with real utility function - does it make reward hacking more difficult? 

Some approaches to alignment rely on identification of agents. Agents can be understoods as algorithms, computations, etc. Can ANN efficiently identify a process as computationally agentic and describe its' algorithm? Toy example that comes to mind is a neural network that takes as input a number series and outputs a formula of function. It would be interesting to see if we can create ANN that can assign computational descriptions to arbirtrary processes.