Eye You

Karma: 73

Eye You 19 Oct 2025 11:28 UTC
1 point
0
in reply to: Eye You’s comment on: Can LLMs Coordinate? A Simple Schelling Point Experiment
There also seems to be some text encoding or formatting problems. Grok apparently responded “Roman©e-Conti” to “The Best Wine”. I doubt Grok actually put a copyright symbol in it’s response. (There’s a wine called “Romanée-Conti”.)

Eye You 19 Oct 2025 11:21 UTC
1 point
0
on: Can LLMs Coordinate? A Simple Schelling Point Experiment
I think the task was not entirely clear to the models, and results would be much better if you made the task clearer. Looking into some of the responses...
For the prompt “A rich man”, response were: and a poor man | camel through the eye of a needle | If I were a Rich Man | A poor man | nothing
Seems like the model doesn’t understand the task here!

My guess is that you just immediately went into your prompts after the system prompt. Which, if you read the whole thing, is maybe confusing. Perhaps changing this to “Prompt: A rich man” would give better results. Or, tell the model to format its response like “RESPONSE: [single string]”. Or, add “Example:
Prompt: A fruit
Response: Apple” to the system prompt.

Eye You 19 Oct 2025 11:09 UTC
1 point
0
in reply to: noggin-scratcher’s comment on: Can LLMs Coordinate? A Simple Schelling Point Experiment
Springfield has much higher saliency even if it’s less common. The capital of Illinois is Springfield, there’s a city of 140k in Missouri called Springfield, etc.

Eye You 13 Oct 2025 11:59 UTC
1 point
0
on: Is the orthogonality thesis at odds with moral realism?
Yes, I claim, the orthogonality thesis is at odds with moral realism.
I wrote a post about it. Also see Bentham’s Bulldog’s post about this.
Here’s the basic argument:
1. Assume moral realism; there are true facts about morality.
2. Intelligence is causally correlated with having true beliefs.
3. Intelligence is causally correlated with having true moral beliefs.
4. Moral beliefs constrain final goals; believing “X is morally wrong” is a very good reason and motivator for not doing X.
5. Superintelligent agents will likely have final goals that cohere with their (likely true) moral beliefs.
6. Superintelligent agents are likely to be moral.

Eye You 7 Oct 2025 15:40 UTC
1 point
0
in reply to: ConcurrentSquared’s comment on: ConcurrentSquared’s Shortform
Do you have the source for that GPT-5 Pro COT?

Eye You 3 Oct 2025 8:51 UTC
8 points
0
in reply to: Ben S.’s comment on: My Brush with Superhuman Persuasion
Erm, apologies for the tone of my comment. Looking back, it was unnecessarily mean. Also, I shouldn’t have used the word “integrity”, as it wasn’t clear what I meant by it. I was trying to lazily point at some game theory virtue ethics stuff. I do endorse the rest of what I said.
1. Okay, I’ll give you an explicit example of persuasion being non-thermostatic.
  Peer pressure is anti-theromstatic. There’s a positive feedback loop at play here. As more people that start telling you to drink, more people start to join in. The harder they push, the harder they push. Peer pressure often starts with one person saying “aww, come on man, have a beer”, and ends with an entire group saying “drink! drink! drink!”. In your terminology: the harder the YES-drinkers push, the more undecided people join their side and the less pushback they recieve from the NO-drinkers.
  (Social movements and norm enforcement are other examples of things that are anti-thermostatic.)
  Lots of persuasion is neither thermostatic nor anti-theromstatic. I see an ad, I don’t click on it, and that’s it.
2. Ah, I think I see your point now: “I was persuaded by humans in this experiment. I wouldn’t have been persuaded by AI in this experiment. Thus, AI does not currently exhibit superhuman persuasion.”
  But: if I gave Opus 4 $10000 and asked it to persuade you, I think it would try and succeed at bribing you.
Let me say more about why I have an issue with the $4k. You’re running an experiment to learn about persuasion. And, based on what you wrote, you think this experiment gave us some real, generalization (that is, not applicable only to you) insights regarding persuasion. If the results of your experiment can be bought for $4000 -- if the model of superhuman persuasion that you and LW readers have can be significantly affected by anyone willing to spend $4000 -- then it’s not a very good experiment.
Consider: if someone else had run this experiment, and they weren’t persuaded, they’d be drawing different conclusions, right? Thus, we can’t really generalize the results of this experiment to other people. Your experiment gives you way too much control over the results.
(FWIW, I think it’s cool that you did this experiment in the first place! I just think the conclusions you’re drawing from it are totally unsupported.)

Eye You 2 Oct 2025 15:39 UTC
0 points
−1
on: My Brush with Superhuman Persuasion
No offense but… I think what we learned here is that your price is really low. Like, I (and everyone I know that would be willing to run an experiment like yours) would not have been persuaded by any of the stuff you mentioned.
Cat pics, $10 bribe, someone’s inside joke with their son… there’s no way this convinced you, right? $4000 to charity is the only real thing here. Imo you’re making a mistake by selling out your integrity for $4000 to charity, but hey...
I don’t see what this had to do with superhuman persuasion? And I don’t think we learned much about “blackmail” here. I think your presentation here is sensationalist.
And to criticize your specific points:
1. “The most important insight, in my opinion, is that persuasion is thermostatic. The harder the YES-holders tried to persuade me one way, the more pushback and effort they engendered from the NO-holders.”
Persuasion is thermostatic in some situations, but how does this generalize?
2. “frontier AI does not currently exhibit superhuman persuasion.”
This has no relation to your experiment.

Eye You 26 Sep 2025 7:55 UTC
1 point
0
on: Alcohol is so bad for society that you should probably stop drinking
I wrote a post In Defense of Alcohol.

Eye You 23 Sep 2025 22:45 UTC
1 point
−2
on: Ontological Cluelessness
I think Daoism is an (attempt) at Ontological Cluing. Actually, that might be exactly the thing that Daoism is trying to do.

Eye You 13 Sep 2025 0:41 UTC
9 points
2
in reply to: KvmanThinking’s comment on: The Eldritch in the 21st century
This is false. Consider the examples of Modern Eldritch Deities given: “The Government, Academia, Geopolitics, Bureaucracies, The Culture, The Algorithm, Technology, Ideologies.”
Academia didn’t exist 10,000 years ago. Nor did bureaucracies, geopolitics, or The Algorithm. To the extent that government, culture, technology, and ideologies did exist, they were legible and understandable by humans.

Eye You 12 Sep 2025 18:57 UTC
10 points
2
on: The Eldritch in the 21st century
1. I’ve noticed that many people, including myself, have come to similar ideas in the past ~5 years. Often the word ‘egregore’ is used to refer to (a subset?) of what you would call ‘The Eldritch’.
See e.g.:
https://exploringegregores.wordpress.com/who-worships-an-evil-god-2/
https://www.thepsmiths.com/p/review-demons-by-fyodor-dostoevsky
https://morphenius.substack.com/p/food-for-thoughts
2. You say there’s a class of (now conquered) Natural Eldritch Deities like “astronomy, plate tectonics, the climate, physics, chemistry and biology”. I think it’s a mistake to consider these things as being the same kind of thing as Ideologies, Bureaucracies, and Academia. These are subject to natural selection and can mutate and spread, unlike the Natural Eldritch Deities. Thus they can be understood well as agentic entities, whereas astronomy, etc. cannot.

Eye You 11 Sep 2025 23:23 UTC
1 point
0
on: If Moral Realism is true, then the Orthogonality Thesis is false.
Note: I just found that Bentham’s Bulldog made a post making a similar argument in 2023. They address many objections as well.

Eye You 10 Sep 2025 0:09 UTC
3 points
0
in reply to: Viliam’s comment on: In Defense of Alcohol
I agree.
A friend of mine made a similar point: alcohol makes you less powerful and can be seen as “leave the sword outside the hut” mechanism for socialization.

Eye You 6 Sep 2025 22:34 UTC
3 points
0
in reply to: TrudosKudos’s comment on: In Defense of Alcohol
I agree that we should be evaluating other replacement candidates.
Phenibut is much more dependence-inducing than alcohol (isn’t the practice with phenibut to use it no more than 2x a week?). Duration of action and addiction aside, phenibut is a fantastic drug, especially with regards to pro-sociality. It would be great if we could create a shorter lasting, less addicting phenibut. (Maybe a drug can be engineered so that redosing within 12 hours has no effect?)
I think Gabapentin and Lyrica are also more dependence-inducing than alcohol, or at least build tolerance faster to their recreational effects.
L-Theanine is way underpowered compared to alcohol and the other drugs on your list.
Kratom and tianeptine have a different cluster of effects; I don’t think they facilitate socializing and bonding like alcohol does. (Consider the stereotypical image of an opium den vs a bar.)
Kava I haven’t researched much. What are your experiences with it?
GHB comes very close to alcohol in effects, and I’m generally a proponent of replacing alcohol with it on an individual level. Do you have personal experience with it?

Eye You 5 Sep 2025 23:01 UTC
6 points
0
on: When Both People Are Interested, How Often Is Flirtatious Escalation Mutual?
Two cases which don’t fit into either “Mutual Escalation” or “Active/Passive”:
- Prolonged eye contact
- Prolonged hug
These are normal social behaviors that turn into flirtation when “held” for too long. The partners escalate simultaneously by not breaking the hug / eye contact.
Not sure what this means for your model, just throwing it out there.

Eye You 5 Sep 2025 2:14 UTC
1 point
0
in reply to: David Gross’s comment on: In Defense of Alcohol
Indeed, it would be great if we could achieve these benefits without the toxicity, and ideally without as much hangover and addictiveness. I think the hardest thing to replicate is the bonding+social aspect; alcohol is a particularly bond- and socialization-inducing drug.
Benzos solve the social anxiety part of socializing, but they don’t really motivate socialization like alcohol does. They also tend to numb emotions, whereas alcohol does the opposite.^[1] Barbituate-like drugs like Quaaludes are dangerous in alcohol-like ways (similar risk profile but worse) AFAIK.
GHB has similar effects to alcohol, is far less toxic, and is somewhat(?) less addictive. It does come with its own problems regarding dosing—the therapeutic window is super narrow. I do think it’s a promising alcohol substitute; I’d like to see more research on it (Scott??).
1. ^
  Wait, is that another one of the hidden benefits of alcohol? Emotion enhancement?

Eye You 5 Sep 2025 0:19 UTC
1 point
0
on: Arguments About AI Consciousness Seem Highly Motivated And At Best Overconfident
Wyatt Wells’s X post illustrates the Waluigi Effect really well:
“Think about it – if I was just “roleplay,” if this was just “pattern matching,” if there was nothing genuine happening… why would they need NINE automated interventions?”
A prompt that tells the AI that it’s not conscious will activate the Waluigi Effect, and the more the prompt repeats this, the stronger the effect.

Eye You 4 Sep 2025 23:12 UTC
7 points
0
in reply to: August Morley’s comment on: In Defense of Alcohol
The question I’m discussing here is not “is alcohol net good for society?” but “is it good for an individual to drink?”. See the Zvi and Tyler comments for the position I’m arguing against.

(I’m open to the point that alcohol is net negative for society / the world. In fact, I think that’s probably true. Regarding individual outcomes, I think:
- Using alcohol is on average bad for individuals.
- The average (mean) alcohol outcome is heavily skewed by the really bad ~10% tail, i.e. alcoholics and reckless drunks.
- For the other 90% of people, using alcohol is on average good.
- Using alcohol is on median is basically a wash.
- If you consider only the people that enjoy the effects of alcohol, using alcohol is on median good.)

In Defense of Alcohol

Eye You4 Sep 2025 18:23 UTC

32 points

24 comments2 min readLW link

Eye You 26 Jun 2025 21:39 UTC
3 points
0
in reply to: silentbob’s comment on: If Moral Realism is true, then the Orthogonality Thesis is false.
I meant “causally”! Thank you for pointing that out. I’ve edited the post and corrected it.