# All of FeepingCreature's Comments + Replies

Disclaimer: I know Said Achmiz from another LW social context.

In my experience, the safe bet is that minds are more diverse than almost anyone expects.

A statement advanced in a discussion like "well, but nobody could seriously miss that X" is near-universally false.

(This is especially ironic cause of the "You don't exist" post you just wrote.)

2Duncan_Sabien4d
Yes, that's why I haven't made any statements like that; I disagree that there's any irony present unless you layer in a bunch of implication and interpretation over top of what I have actually said. (I refer you to guideline 7.)

Not wanting to disagree or downplay, I just want to offer a different way to think about it.

When somebody says I don't exist - and this definitely happens - to me, it all depends on what they're trying to do with it. If they're saying "you don't exist, so I don't need to worry about harming you because the category of people who would be harmed is empty", then yeah I feel hurt and offended and have the urge to speak up, probably loudly. But if they're just saying when trying to analyze reality, like, "I don't think people like that exist, because my model ...

Or maybe you're just the right amount of optimistic for the people you've run into, and I'm just less lucky. =P

I'll cheat and give you the ontological answer upfront: you're confusing the alternate worlds simulated in your decision algorithm with physically real worlds. And the practical answer: free will is a tool for predicting whether a person is amenable to persuasion.

Smith has a brain tumor such that he couldn’t have done otherwise

Smith either didn't simulate alternate worlds, didn't evaluate them correctly or the evaluation didn't impact his decisionmaking; there is no process flow through outcome simulation that led to his action. Instead of "I want X de...

3Gerald Monroe13d
So essentially it's a question of "COULD the actor have considered societal rules and consequences before acting". This makes sense on brain tumor vs not cases. But what about "they got drunk and then committed murder". They were unable to consider the consequences/not murder when drunk. Hypothetically they don't know that becoming drunk makes you homicidal. Or the "ignorance of the law is not an excuse". A lot of these interpretations end up being "we know they probably didn't have any form of ability to not commit this crime but we are going to punish anyway just in case they might". Maybe they read that particular law about importing shellfish buried in federal code and just lied and said they didn't know. Maybe they actually knew getting drunk makes them want to murder and they drank anyway. Punishment for societal convenience.

Sounds like regret aversion?

edit: Hm, you're right that optionality is kind of an independent component.

tl;dr: don't overanalyze the final cause of disaster; usually it was preceded by serial failure of prevention mechanisms, any one or all of which can be improved for risk reduction.

5Gerald Monroe1mo
Yeah but false positive. Every time anyone mentions all the ignored warnings they never try to calculate how many times the same warning occurred and everything was fine? It's easy to point to O rings after the space shuttle is lost. But how many thousand other weak links were NASA/contractor engineers concerned about?

If your son can't tell the difference between the risk profiles of LSD and heroin, something has gone wrong in your drug education. Maybe it's the overly simplistic "drugs are bad" messaging? Maybe a "drugs have varying levels of risk in multiple dimensions" messaging would avoid embarrassing events like comparing LSD with coffee - because yes, coffee is a drug that affects the brain. Wouldn't be much use if it didn't. It even creates a tolerance, forcing increasingly higher doses. So it is in fact quite hard to draw a hard line between coffee, LSD, mariju...

5the gears to ascenscion2mo
if you simply drop the word drugs and try to figure out which chemicals are dangerous to consume, it might be even easier. also potentially worth bringing up is that the human brain is typically near optimality in most ways and it is usually quite hard to identify specific ways to alter your brain to improve it. this is similar to taking a trained neural network and attempting to update it significantly with a sampling setting or inference change: maybe you can re-architect it after training and not do any more training updates and still get something useful out of the inference invocation, but more likely the neural net breaks, and when you are the neural network in question and don't have the opportunity to roll back changes, it is very risky to do experimentation. if your research is wrong about how quickly damage accumulates from a change, it can be very bad! also, an important factor in learning is to have higher risk tolerance for some period of time in order to gain the experience to calibrate your risk estimates. without that you don't explore, you spend all your time using whatever few things you know about! and humans of course have this built-in, we wouldn't be able to grow up otherwise. unfortunately it can have some pretty serious consequences if people don't realize their risk tolerance is unusually high when they're young, for example I was very hesitant to drive cars until I was 19 because of the way the risk tolerance curve changes. The accident rate per capita of a newly licensed 16-year-old driver is far higher than that of a 19-year-old, because of this risk tolerance curve. any type of risk of permanent damage meshes badly with this; it's the first person version of one of the key components to AI safety, avoiding irreversible state transitions from curious reinforcement learners.

So IIUC, would you expect RLHF to, for instance, destroy not just the model's ability to say racist slurs, but its ability to model that anybody may say racist slurs?

Do you think OpenAI's "As a language model trained by OpenAI" is trying to avoid this by making the model condition proper behavior on its assigned role?

5Charlie Steiner2mo
I usually don't think of it on the level of modeling humans who emit text. I mostly just think of it on the level of modeling a universe of pure text, which follows its own "semiotic physics" (reference post forthcoming from Jan Kirchner). That's the universe in which it's steering trajectories to avoid racist slurs. I think OpenAI's "as a language model" tic is trying to make ChatGPT sound like it's taking role-appropriate actions in the real world. But it's really just trying to steer towards parts of the text-universe where that kind of text happens, so if you prompt it with the text "As a language model trained by OpenAI, I am unable to have opinions," it will ask you questions that humans might ask, to keep the trajectory going (including potentially offensive questions if the reward shaping isn't quite right - though it seems pretty likely that secondary filters would catch this.)

Yes, this effectively forces the network to use backward reasoning. It's equivalent to saying "Please answer without thinking, then invent a justification."

The whole power of chains-of-thought comes from getting the network to reason before answering.

When we get results that it is easy for you to be afraid of, it will be firmly too late for safety work.

How does this handle the situation where the AI, in some scenario, picks up the idea of "deception" and then, when it describes its behavior honestly by intending to mislead the observer into thinking that it is honest, due to noticing that it is probably inside a training scenario, then gets reinforcement trained on dishonest behaviors that present as honest, ie. deceptive honesty?

3Michael Soareverix5mo
I'm not sure exactly what you mean. If we get an output that says "I am going to tell you that I am going to pick up the green crystals, but I'm really going to pick up the yellow crystals", then that's a pretty good scenario, since we still know its end behavior. I think what you mean is the scenario where the agent tells us the truth the entire time it is in simulation but then lies in the real world. That is definitely a bad scenario. And this model doesn't prevent that from happening.  There are ideas that do (deception takes additional compute vs honesty, so you can refine the agent to be as efficient as possible with its compute). However, I think the biggest space of catastrophe is basic interpretability. We have no idea what the agent is thinking because it can't talk with us. By allowing it to communicate and training it to communicate honestly, we seem to have a much greater chance of getting benevolent AI. Given the timelines, we need to improve our odds as much as possible. This isn't a perfect solution, but it does seem like it is on the path to it.

Hm, difficult. I think the minimal required trait is the ability to learn patterns that map outputs to deferred reward inputs. So an organism that simply reacts to inputs directly would not be an optimizer, even if it has a (static) nervous system. A test may be if the organism can be made to persistedly change strategy by a change in reward, even in the immediate absence of the reward signal.

I think maybe you could say that ants are not anthill optimizers? Because the optimization mechanism doesn't operate at all on the scale of individual ants? Not sure if that holds up.

I think a bacterium is not an optimizer. Rather, it is optimized by evolution. Animals start being optimizers by virtue of planning over internal representations of external states, which makes them mesaoptimizers of evolution.

If we follow this model, we may consider that optimization requires a map-territory distinction. in that view, DNA is the map of evolution, and the CNS is the map of the animal. If the analogy holds, I'd speculate that the weights are the map of reinforcement learning, and the context window is the map of the mesaoptimizer.

2shminux7mo
Hmm, so where does the "true" optimization start? Or, at least what is the range of living creatures which are not-quite-complex to count as optimizers? Clearly a fish would be one, right? What about a sea cucumber? A plant?

Most multiplayer games have some way to limit XP gain from encounters outside your difficulty, to avoid exactly this sort of cheesing. The worry is that it allows players to get through the content quicker, with (possibly paid) help from others, which presumably makes it less likely they'll stick around.

(Though of course an experienced player can still level vastly faster, since most players don't take combat anywhere near optimally to maximize xp gain.)

That said, Morrowind famously contains an actual intelligence explosion. So you tend to see this sort of...

Resources used in pressuring corporations are unlikely to have any effect which increases AI risk.

Devil's advocate: If this unevenly delays corporations sensitive to public concerns, and those are also corporations taking alignment at least somewhat seriously, we get a later but less safe takeoff. Though this goes for almost any intervention, including to some extent regulatory.

5Lone Pine10mo
Yes. An example of how this could go disastrously wrong is if US research gets regulated but Chinese research continues apace, and China ends up winning the race with a particularly unsafe AGI.

I don’t understand why you would want to spend any effort proving that transformers could scale to AGI.

The point would be to try and create common knowledge that they can. Otherwise, for any "we decided to not do X", someone else will try doing X, and the problem remains.

Humanity is already taking a shotgun approach to unaligned AGI. Shotgunning safety is viable and important, but I think it's more urgent to prevent the first shotgun from hitting an artery. Demonstrating AGI viability in this analogy is shotgunning a pig in the town square, to prove to ...

I'm actually optimistic about prosaic alignment for a takeoff driven by language models. But I don't know what the opportunity for action is there - I expect Deepmind to trigger the singularity, and they're famously opaque. Call it 15% chance of not-doom, action or no action. To be clear, I think action is possible, but I don't know who would do it or what form it would take. Convince OpenAI and race Deepmind to a working prototype? This is exactly the scenario we hoped to not be in...

edit: I think possibly step 1 is to prove that Transformers can scale to...

4Lone Pine10mo
I'm definitely on board with prosaic alignment via language models. There's a few different projects I've seen in this community related to that approach, including ELK and the project to teach a GPT-3-like model to produce violence-free stories. I definitely think these are good things. I don't understand why you would want to spend any effort proving that transformers could scale to AGI. Either they can or they can't. If they can, then proving that they can will only accelerate the problem. If they can't, then prosaic alignment will turn out to be a waste of time, but only in the sense that every lightbulb Edison tested was a waste of time (except for the one that worked). This is what I mean by a shotgun approach.

If these paths are viable, I desire to believe that they are viable.

If these paths are nonviable, I desire to believe that they are nonviable.

Does it do any good, to take well-meaning optimistic suggestions seriously, if they will in fact clearly not work? Obviously, if they will work, by all means we should discover that, because knowing which of those paths, if any, is the most likely to work is galactically important. But I don't think they've been dismissed just because people thought the optimists needed to be taken down a peg. Reality does not owe us...

I have a reasonably low value for p(Doom).  I also think these approaches (to the extent they are courses of action) are not really viable.  However, as long as they don't increase the probability of p(Doom) its fine to pursue them.  Two important considerations here:  an unviable approach may still slightly reduce p(Doom) or delay Doom and the resources used for unviable approaches don't necessarily detract from the resources used for viable approaches.

For example, "we'll pressure corporations to take these problems seriously", while u...

3Lone Pine10mo
What is p(DOOM | Action), in your view?
1. As I understand it, OpenAI argue that GPT-3 is a mesa-optimizer (though not in those terms) in the announcement paper Language Models are Few-Shot Learners. (Search for meta.) (edit: Might have been in another paper. I've seen this argued somewhere, but I might have the wrong link :( ) Paraphrased, the model has been shown so many examples of the form "here are some examples that create an implied class, is X an instance of the class? Yes/no", that instead of memorizing the answers to all the questions, it has acquired a general skill for abstracting at r
...

How much would your view shift if there was a model that could "engineer its own prompt", even during training?

3lorepieri10mo
A close call, but I would lean still on no. Engineering the prompt is where humans leverage all their common sense and vast (w.r.t.. the AI) knowledge.

I meant it's a hard bet to win because how exactly would I collect. That said, I'm genuinely not sure if it's a good field for betting. Roughly speaking, there's two sorts of bets: "put your money where your mouth is" bets and "hedging" bets. The former are "for fun" and signaling/commitment purposes; the latter are where the actual benefit comes in. But with both bets, it's difficult to figure out a bet structure that works if the market gets destroyed in the near future! We could bet on confidence, but I'm genuinely not sure if there'll be one or two "bi...

A system that contains agents is a system that is dangerous, it doesn't have to "be" an agent. Arguably PaLM already contains simple agents. This is why it's so important that it understands jokes, because jokes contain agents that are mistaken about the world, which implies the capability to model people with different belief states.

Imagine a human captured by a mind control fungus, and being mind controlled to not replicate and to do no harm. Also the entire planet is covered with the fungus and the human hates it and wants it to be dead, because of the mind control. (This is not an AI analogy, just an intuition pump to get the human in the right mindset.) Also the fungus is kind of stupid, maybe 90 IQ by human standards for its smartest clusters. What rules could you, as the fungus, realistically give the human, that doesn't end up with "our entire planet is now on fire" or "we have...

That seems like a hard bet to win. I suggest instead offering to bet on "you will end up less worried" vs "I will end up more worried", though that may not work.

2IlyaShpitser10mo
If you think it's a hard bet to win, you are saying you agree that nothing bad will happen.  So why worry?
3shiney10mo
I don't think it's that hard e.g see here https://www.econlib.org/archives/2017/01/my_end-of-the-w.html [https://www.econlib.org/archives/2017/01/my_end-of-the-w.html] TLDR person who doesn't think end of the world will happen gives other person money now and it gets paid back double if the world doesn't end.

Katja Grace's 2015 survey of NIPS and ICML researchers provided an aggregate forecast giving a 50% chance of HLMI occurring by 2060 and a 10% chance of it occurring by 2024.

2015 feels decades ago though. That's before GPT-1!

(Today, seven years after the survey was conducted, you might want to update against the researchers that predicted HLMI by 2024.)

I would expect a survey done today to have more researchers predicting 2024. Certainly I'd expect a median before 2060! My layman impression is that things have turned out to be easier to do for big language ...

3aogara6mo
This was heavily upvoted at the time of posting, including by me. It turns out to be mostly wrong. AI Impacts just released a survey of 4271 NeurIPS and ICML researchers conducted in 2021 and found that the median year for expected HLMI is 2059, down only two years from 2061 since 2016. Looks like the last five years of evidence hasn’t swayed the field much. My inside view says they’re wrong, but the opinions of the field and our inability to anticipate them are both important. https://aiimpacts.org/2022-expert-survey-on-progress-in-ai/ [https://aiimpacts.org/2022-expert-survey-on-progress-in-ai/]

Just delete the context window and tweak the prompt.

4jeff876510mo
But this doesn’t solve the problem of angry customers and media the way firing a misbehaving employee would. Though I suppose this is more an issue of friction/aversion to change than an actual capabilities issue.

Well, if we get to AGI from NLP, ie. a model trained on a giant human textdump, I think that's promising because we're feeding it primarily data that's generated by the human ontology in the first place, so the human ontology would plausibly be the best compressor for it.

I wonder what the failure probability is for human customer service employees.

4jeff876510mo
Likely higher than one in a million, but they can be fired after a failure to allow the company to save face. Harder to do that with a \$50M language model.

Now I'm not saying it's anthropic pressure, but if that's true maybe we shouldn't just keep training until we know what exactly it is that the model is grokking.

5Throwaway236710mo
Whatever is happening, I'm really concerned about the current "sufficiently big model starts to exhibit <weird behaviour A>. I don't understand, but also don't care, here is a dirty workaround and just give it more compute lol" paradigm. I don't think this is very safe.

Trying to solve the LessWrong Community Alignment Problem?

Good question. What my intuition says is "even if you have a snapshot at a certain point, if it was generated randomly, there is no way to get the next snapshot from it." Though maybe it would be. If so, I think it's not just conscious but me in every regard. - I don't know if this is physically coherent, but if we imagine a process by which you can gain answers to every important question about the current state but very little information about the next state, then I don't think this version of me would be conscious. - That said, if you can also query in...

Sorta. Fully agreed with the second. I'm not sure I believe in a state-process distinction- I don't think that if you randomly pulled a snapshot of a brain very much like mine out of a hat, that that snapshot would be phenomenologically conscious, though of course as per follow-the-improbability I wouldn't expect you to actually do this. Rather, the pattern of "my brain, ie. subset <small number> of iteration <large number> of <grand unified theory of physics> is conscious." Ie. I believe in state only inasmuch as it's the output of a pro...

4Rafael Harth10mo
Still not sure if I understand this. I guess two things that confuse me about this One, say the 1 to 10400 or whatever probability event happens and some random process by chance generates a snapshot of your brain. How does the universe know that this is not conscious? Two, if you require process, what is the difference between this and FR? Is there any scenario where the distinction matters?

Is my answer (patternism/mathematical monadism) separate from reductive functionalism? My view is that the algorithmic description of my brain is already phenomenologically conscious; physically evaluating it accesses these experiences but does not create them. I think the materialist view still holds that there is some sort of "secret fire" to things actually physically happening.

(If not, just count me under red func.)

4Rafael Harth10mo
Tell me if this summary of that view is correct: * consciousness is a state, not a process. you can look at [a pattern of atoms] at one point in time and say "this is conscious" * whether something is conscious can be decided entirely on a level of abstraction above the physical (presumably the algorithmic level) If so, this is separate from the description I've given in the survey, although I believe Eliezer never explicitly draws the state/process distinction in the sequences. It looks to me like an FR/panpsychism hybrid with the "state" from panpyschism but the "algorithmic description is what counts" from FR.

The biggest stretch here seems to me to be evaluating the brain on the basis of how much compute existing hardware requires to emulate the brain. Ultimately, this is biased towards the conclusion, because, to slightly parody your position, the question you end up asking is "how much brain do you need to simulate one brain," determining that the answer is "one brain", and then concluding that the brain is perfectly efficient at being itself. However, the question of how much of the compute that is being attributed to the brain here is actually necessary for...

6jacob_cannell1y
I'm going to resist the urge to parody/strawman your parody/strawman, and so instead I improved the circuits section especially, and clarified the introduction to more specifically indicate how efficiency relates only to the types of computations brains tend to learn (evolutionarily relevant cognition), and hopefully prevent any further confusion of simulation with emulation.

The biggest stretch here seems to me to be evaluating the brain on the basis of how much compute existing hardware requires to emulate the brain.

Where did I do that? I never used emulation in that context. Closely emulating a brain - depending on what you mean - could require arbitrarily more compute then the brain itself.

You may be confused by my comparisons to GPUs? That is to establish points of comparison. Naturally it also relates to the compute/energy c...

I think what happened is the Wesley twins noticed that they had contradictory beliefs:

1. "We've been to every room"
2. "We've seen the Chamber of Secrets on the map before"
3. "We haven't been in the CoS"

Thus they know for a fact that something about the map is fucking with their memory or perception. Hence "Someone said a rude word."

Old LessWrong meme - phyg is rot13 cult. For a while people were making "are we a cult" posts so much that it was actually messing with LessWrong's SEO. Hence phyg.

Common question: "Well, but what if God was real and actually appeared to you in flame and glory, wouldn't it be silly to not be convinced in that case?"

My answer: "I don't know, do you think my thought patterns are likely to be deployed in such an environment?"

1Boris Kashirin1y
How about historical precedent? Gods did arrive on Spanish ships to South America.
4shminux1y
That's another way to look at it. The usual implicit assumptions break down on the margins. Though, given the odds of this happening (once in a bush, at best, and the flame was not all that glorious), I would bet on hallucinations as a much likelier explanation. Happens to people quite often.

I think it can be reasonable to have 100% confidence in beliefs where the negation of the belief would invalidate the ability to reason, or to benefit from reason. Though with humans, I think it always makes sense to leave an epsilon for errors of reason.

I don't think the verbal/pre-verbal stream of consciousness that describes our behavior to ourselves is identical with ourselves. But I do think our brain exploits it to exert feedback on its unconscious behavior, and that's a large part of how our morality works. So maybe this is still relevant for AI safety.

That's true, but ... I feel in most cases, it's a good idea to run mixed strategies. I think that by naivety I mean the notion that any single strategy will handle all cases - even if there are strategies where this is true, it's wrong for almost all of them.

Humans can be stumped, but we're fairly good at dynamic strategy selection, which tends to protect us from being reliably exploited.

Humans can be stumped, but we're fairly good at dynamic strategy selection, which tends to protect us from being reliably exploited.

Have you ever played Far Cry 4? At the beginning of that game, there is a scene where you're being told by the main villain of the storyline to sit still while he goes downstairs to deal with some rebels. A normal human player would do the expected thing, which is to curiously explore what's going on downstairs, which then leads to the unfolding of the main story and thus actual gameplay. But if you actually stick to the villa...

Well, one may develop an AI that handles noisy TV by learning that it can't predict the noisy TV. The idea was to give it a space that is filled with novelty reward, but doesn't lead to a performance payoff.

What would stump a (naive) exploration-based AI? One may imagine a game as such: the player starts on the left side of a featureless room. If they go to the right side of the room, they win. In the middle of the room is a terminal. If one interacts with the terminal, one is kicked into an embedded copy of the original Doom.

An exploration-based agent would probably discern that Doom is way more interesting than the featureless room, whereas a human would probably put it aside at some point to "finish" exploring the starter room first. I think this demands a sort of mixed breadth-depth exploration?

3maximkazhenkov1y
You could certainly engineer an adversarial learning environment to stump an exploration-based AI, but you could just as well engineer an adversarial learning environment to stump a human. Neither is "naive" because of it in any useful sense, unless you can show that that adversarial environment has some actual practical relevance.
8gwern1y
Even defining what is a 'featureless room' in full generality is difficult. After all, the literal pixel array will be different at most timesteps (and even if ALE games are discrete enough for that to not be true, there are plenty of environments with continuous state variables that never repeat exactly). That describes the opening room of Montezuma's Revenge: you have to go in a long loop around the room, timing a jump over a monster that will kill you, before you get near the key which will give you the first reward after hundreds of timesteps. Go-Explore can solve MR and doesn't suffer from the noisy TV problem because it does in fact do basically breadth+depth exploration (iterative widening), but it also relies on a human-written hack for deciding what states/nodes are novel or different from each other and potentially worth using as a starting point for exploration.

The famous problem here is the "noisy TV problem". If your AI is driven to go towards regions of uncertainty then it will be completely captivated by a TV on the wall showing random images, no need for a copy of Doom, any random giberish that the AI can't predict will work.

Sure, but that definition is so generic and applies to so many things that are obviously not like human pain (landslides?) that it lacks all moral compulsion.

Counterexample:

Oh God! I am in horrible pain right now! For no reason, my body feels like it's on fire! Every single part of my body feels like it's burning up! I'm being burned alive! Help! Please make it stop! Help me!!

Okay, so that thing that I just said was a lie. I was not actually in pain (I can confirm this introspectively); instead, I merely pretended to be in pain.

Sir Ian McKellen has an instructive video.

The Turing test works for many things, but I don't think it works for checking for the existence of internal phenomenological states. If you ask...

3Logan Zoellner1y
I think  we  both agree that GPT-3 does not feel pain.   However, under a particular version of pan-psychism: "pain is any internal state which a system attempts to avoid", GPT obviously would qualify.

I mostly see where you're coming from, but I think the reasonable answer to "point 1 or 2 is a false dichotomy" is this classic, uh, tumblr quote (from memory):

"People cannot just. At no time in the history of the human species has any person or group ever just. If your plan relies on people to just, then your plan will fail."

This goes especially if the thing that comes after "just" is "just precommit."

My expectation is that interaction with Vassar is that the people who espouse 1 or 2 expect that the people interacting are incapable of precommitting to th...

This is a very good criticism! I think you are right about people not being able to "just."

My original point with those strategies was to illustrate an instance of motivated stopping about people in the community who have negative psychological effects, or criticize popular institutions. Perhaps it is the case that people genuinely tried to make a strategy but automatically rejected my toy strategies as false. I do not think it is, based on "vibe" and on the arguments that people are making, such as "argument from cult."

I think you are actually completely ...

I don't think Scott is claiming it's arbitrary, I think he's claiming it's subjective, which is to say instrumental. As Eliezer kept pointing out in the morality debates, subjective things are objective if you close over the observer - human (ie. specific humans') morality is subjective, but not arbitrary, and certainly not unknowable.

But also I don't think that phylo categorization is stronger per se than niche categorization in predicting animal behavior, especially when it comes to relatively mutable properties like food consumption. Behavior, body shap...

I think this is either basic psychology or wrong.¹

For one, Kant seems to be conflating the operation of a concept with its perception:

Since the concept of “unity” must exist for there to be combination (or “conjunction”) in the first place, unity can’t come from combination itself. The whole-ness of unified things must be a product of something beyond combination.

This seems to say that the brain cannot unify things unless it has a concept of combination. However, just as an example, reinforcement learning in AI shows this to be false: unification can ...

There was a comment here, but I completely wiped it because it was too confused.

Sorry, but I can no longer participate in the free-will debate. Apparently I have unlearnt how to think in that particular broken way. Anything that has to do with indeterminism relating to choice is no longer legible to me.

I have sort of unlearnt how to think of free will in a nondeterministic sense. As such, I tripped over the part where you said there were "arguments against free will." Like, yes of course the sensation of volition is produced by a deterministic, predictable process; how else could it be about the deciding process? Aboutness only exists in causal systems.

A more interesting question may be what the sensation is for? What part of our high-level cognition depends on noticing that we are making a decision?

2DirectedEvolution2y
This post will make more sense if you read the linked post by Eliezer at the top. In it, he asks you to identify a "cognitive algorithm" by which the very idea that there is a debate between "free will" and "determinism" feels like it makes psychological sense.

A variable is just a pure function with no parameters.

Right, but in the naming style I know, promotedPosts would never have a visible side effect, because it's a noun. Side-effectful functions have imperative names, promotePosts - and never the two shall mix.