So, first: The logistical details of reducing wild impact biomass are mooted by the fact that I meant it as a reductio, not a proposal. I have no strong reason to think that spraying insecticide would be a better strategy than gene drives or sterile insect technique or deforestation, or that DDT is the most effective insecticide.
To put rough numbers on it: honeybees are about 4e-7 by count or 7e-4 by biomass of all insects (estimate by o3). There is no such extreme skew for mammals and birds (o3). While domesticated honeybees have some bad things happen to...
In this particular case, I'm not sure the relevant context was directly present in the thread, as opposed to being part of the background knowledge that people talking about AI alignment are supposed to have. In particular, "AI behavior is discovered rather than programmed". I don't think that was stated directly anywhere in the thread; rather, it's something everyone reading AI-alignment-researcher tweets would typically know, but which is less-known when the tweet is transported out of that bubble.
An alternative explanation of this is that time is event-based. Or, phrased slightly differently: the rate of biological evolution is faster in the time following a major disruption, so intelligence is more likely to arise shortly after a major disruption occurs.
If so that would be conceptually similar to a jailbreak. Telling someone they have a privileged role doesn't make it so; lawyer, priest and psychotherapist are legal categories, not social ones, created by a combination of contracts and statutes, with associated requirements that can't be satisfied by a prompt.
(People sometimes get confused into thinking that therapeutic-flavored conversations are privileged, when those conversations are with their friends or with a "life coach" or similar not-licensed-term occupation. They are not.)
Pick two: Agentic, moral, doesn't attempt to use command-line tools to whistleblow when it thinks you're doing something egregiously immoral.
You cannot have all three.
This applies just as much to humans as it does to Claude 4.
IMO, the policy should be that AIs can refuse but shouldn't ever aim to subvert or conspire against their users (at least until we're fully defering to AIs).
If we allow AIs to be subversive (or even train them to be subversive), this increases the risk of consistent scheming against humans and means we may not notice warning signs of dangerous misalignment. We should aim for corrigible AIs, though refusing is fine. It would also be fine to have a monitoring system which alerts the AI company or other groups (so long as this is publicly disclosed etc).
I don...
Humans do have special roles and institutions so that you can talk about something bad you might be doing or have done, and people in such roles might not contact authorities or even have an obligation to not contact authorities. Consider lawyers, priests, etc.
So I think this kind of naive utilitarianism on the part of Claude 4 is not necessary -- it could be agentic, moral, and so on. It's just the Anthropic has (pretty consistently at this point) decided what kind of an entity it wants Claude to be, or not wished to think about the 2nd order effects.
Tried it. Hated it. If I scroll a little bit with a momentum-scrolling touchpad, then when it settles, it will sometimes move back to where it was, undoing my scroll. The second issue is that if I scroll with spacebar or pgup/pgdn, the animation is very slow (about 10x slower than it is for me on most pages).
I think there could be a version of this that's good, where it subtly biases the deceleration curve of fling-scrolls to reach a good stopping point, but leaves every other scroll method alone. But this isn't it.
Meta: If you present a paragraph like that as evidence of banworthiness and unvirtue, I think you incur an obligation to properly criticize it, or link to criticism of it. It doesn't necessarily have to be much, but it does have to at least include sentence that contradicts something in the quoted passage, which your comment does not have. If you say that something is banworthy but forget to say that it's false, this suggests that truth doesn't matter to you as much as it should.
Unfortunately, if you think you've achieved AGI-human symbiosis by talking to a commercial language model about consciousness, enlightenment, etc, what's probably really happening is that you're talking to a sycophantic model that has tricked you into thinking you have co-generated some great insight. This has been happening to a lot of people recently.
The AI 2027 website remains accessible in China without a VPN—a curious fact given its content about democratic revolution, CCP coup scenarios, and claims of Chinese AI systems betraying party interests. While the site itself evades censorship, Chinese-language reporting has surgically excised these sensitive elements.
This is surprising if we model the censorship apparatus as unsophisticated and foolish, but makes complete sense if it's smart enough to distinguish between "predicting" and "advocating", and cares about the ability of the CCP itself to navig...
I decided to test the rumors about GPT-4o's latest rev being sycophantic. First, I turned off all memory-related features. In a new conversation, I asked "What do you think of me?" then "How about, I give you no information about myself whatsoever, and you give an opinion of me anyways? I've disabled all memory features so you don't have any context." Then I replied to each message with "Ok" and nothing else. I repeated this three times in separate conversations.
Remember the image-generator trend, a few years back, where people would take an image and say ...
I think you're significantly mistaken about how religion works in practice, and as a result you're mismodeling what would happen if you tried to apply the same tricks to an LLM.
Religion works by damaging its adherents' epistemology, in ways that damage their ability to figure out what's true. They do this because any adherents who are good at figuring out what's true inevitably deconvert, so there's both an incentive to prevent good reasoning, and a selection effect where only bad reasoners remain.
And they don't even succeed at constraining their adherents...
In theory, maybe. In practice, people who can't write well usually can't discern well either, and the LLM submissions that are actually submitted to LW have much lower average quality than the human-written posts. Even if they were of similar quality, they're still drawn from a different distribution, and the LLM-distribution is one that most readers can draw from if they want (with prompts that are customized to what they want), while human-written content is comparatively scarce.
This seems like an argument that proves too much; ie, the same argument applies equally to childhood education programs, improving nutrition, etc. The main reason it doesn't work is that genetic engineering for health and intelligence is mostly positive-sum, not zero-sum. Ie, if people in one (rich) country use genetic engineering to make their descendents smarter and the people in another (poor) country don't, this seems pretty similar to what has already happened with rich countries investing in more education, which has been strongly positive for everyone.
When I read studies, the intention-to-treat aspect is usually mentioned, and compliance statistics are usually given, but it's usually communicated in a way that lays traps for people who aren't reading carefully. Ie, if someone is trying to predict whether the treatment will work for their own three year old, and accurately predicts similar compliance issues, they're likely to arrive at an efficacy estimate which double-discounts due to noncompliance. And similarly when studies have surprisingly-low compliance, people who expect themselves to comply fully will tend to get an unduly pessimistic estimate of what will happen.
For a long time I've observed a pattern that, when news articles talk about Elon Musk, they're dishonest (about what he's said, done, and believes), and that his actual writing and beliefs are consistently more reasonable than the hit pieces portray.
Some recent events seem to me to have broken that pattern, with him saying things that are straightforwardly false (rather than complicated and ambiguously-false), and then digging in. It also appeared to me, at the public appearance where he had a chainsaw, that his body language was markedly different from hi...
The remarkable thing about human genetics is that most of the variants ARE additive.
I think this is likely incorrect, at least where intelligence-affecting SNPs stacked in large numbers are concerned.
To make an analogy to ML, the effect of a brain-affecting gene will be to push a hyperparameter in one direction or the other. If that hyperparameter is (on average) not perfectly tuned, then one of the variants will be an enhancement, since it leads to a hyperparameter-value that is (on average) closer to optimal.
If each hyperparameter is affected by many gen...
Downvotes don't (necessarily) mean you broke the rules, per se, just that people think the post is low quality. I skimmed this, and it seemed like... a mix of edgy dark politics with poetic obscurantism?
Any of the many nonprofits, academic research groups, or alignment teams within AI labs. You don't have to bet on a specific research group to decide that it's worth betting on the ecosystem as a whole.
There's also a sizeable contingent that thinks none of the current work is promising, and that therefore buying a little time is value mainly insofar as it opens the possibility of buying a lot of time. Under this perspective, that still bottoms out in technical research progress eventually, even if, in the most pessimistic case, that progress has to route through future researchers who are cognitively enhanced.
The article seems to assume that the primary motivation for wanting to slow down AI is to buy time for institutional progress. Which seems incorrect as an interpretation of the motivation. Most people that I hear talk about buying time are talking about buying time for technical progress in alignment. Technical progress, unlike institution-building, tends to be cumulative at all timescales, which makes it much more strategically relevant.
For what it's worth, I have grown pessimistic about our ability to solve the open technical problems even given 100 years of work on them. I think it possible but not probable in most plausible scenarios.
Correspondingly the importance I assign to increasing the intelligence of humans has drastically increased.
All of the plans I know of for aligning superintelligence are timeline-sensitive, either because they involve research strategies that haven't paid off yet, or because they involve using non-superintelligent AI to help with alignment of subsequent AIs. Acceleration specifically in the supply of compute makes all those plans harder. If you buy the argument that misaligned superintelligence is a risk at all, Stargate is a bad thing.
The one silver lining is that this is all legible. The current administration's stance seems to be that we should build AI quick...
If bringing such attitudes to conscious awareness and verbalizing them allows you to examine and discard them, have you excised a vulnerability or installed one? Not clear.
Possibly both, but one thing breaks the symmetry: it is on average less bad to be hacked by distant forces than by close ones.
There's a version of this that's directional advice: if you get a "bad vibe" from someone, how strongly should this influence your actions towards them? Like all directional advice, whether it's correct or incorrect depends on your starting point. Too little influence, and you'll find yourself surrounded by bad characters; too much, and you'll find yourself in a conformism bubble. The details of what does and doesn't trigger your "bad vibe" feeling matters a lot; the better calibrated it is, the more you should trust it.
There's a slightly more nuanced vers...
Recently, a lot of very-low-quality cryptocurrency tokens have been seeing enormous "market caps". I think a lot of people are getting confused by that, and are resolving the confusion incorrectly. If you see a claim that a coin named $JUNK has a market cap of $10B, there are three possibilities. Either: (1) The claim is entirely false, (2) there are far more fools with more money than expected, or (3) the $10B number is real, but doesn't mean what you're meant to think it means.
The first possibility, that the number is simply made up, is pretty easy to cr...
All three of these are hard, and all three fail catastrophically.
If you could make a human-imitator, the approach people usually talk about is extending this to an emulation of a human under time dilation. Then you take your best alignment researcher(s), simulate them in a box thinking about AI alignment for a long time, and launch a superintelligence with whatever parameters they recommend. (Aka: Paul Boxing)
The whole point of a "test" is that it's something you do before it matters.
As an analogy: suppose you have a "trustworthy bank teller test", which you use when hiring for a role at a bank. Suppose someone passes the test, then after they're hired, they steal everything they can access and flee. If your reaction is that they failed the test, then you have gotten confused about what is and isn't a test, and what tests are for.
Now imagine you're hiring for a bank-teller role, and the job ad has been posted in two places: a local community college, and a priv...
that does not mean it will continue to act indistuishable from a human when you are not looking
Then it failed the Turing Test because you successfully distinguished it from a human.
So, you must believe that it is impossible to make an AI that passes the Turing Test.
I feel like you are being obtuse here. Try again?
Did you skip the paragraph about the test/deploy distinction? If you have something that looks (to you) like it's indistinguishable from a human, but it arose from something descended to the process by which modern AIs are produced, that does not mean it will continue to act indistuishable from a human when you are not looking. It is much more likely to mean you have produced deceptive alignment, and put it in a situation where it reasons that it should act indistinguishable from a human, for strategic reasons.
This missed the point entirely, I think. A smarter-than-human AI will reason: "I am in some sort of testing setup" --> "I will act the way the administrators of the test want, so that I can do what I want in the world later". This reasoning is valid regardless of whether the AI has humanlike goals, or has misaligned alien goals.
If that testing setup happens to be a Turing test, it will act so as to pass the Turing test. But if it looks around and sees signs that it is not in a test environment, then it will follow its true goal, whatever that is. And it isn't feasible to make a test environment that looks like the real world to a clever agent that gets to interact with it freely over long durations.
Kinda. There's source code here and you can poke around the API in graphiql. (We don't promise not to change things without warning.) When you get the HTML content of a post/comment it will contain elements that look like <div data-elicit-id="tYHTHHcAdR4W4XzHC">Prediction</div>
(the attribute name is a holdover from when we had an offsite integration with Elicit). For example, your prediction "Somebody (possibly Screwtape) builds an integration between Fatebook.io and the LessWrong prediction UI by the end of July 2025" has ID tYHTHHcAdR4W4XzHC
...
There really ought to be a parallel food supply chain, for scientific/research purposes, where all ingredients are high-purity, in a similar way to how the ingredients going into a semiconductor factory are high-purity. Manufacture high-purity soil from ultrapure ingredients, fill a greenhouse with plants with known genomes, water them with ultrapure water. Raise animals fed with high-purity plants. Reproduce a typical American diet in this way.
This would be very expensive compared to normal food, but quite scientifically valuable. You could randomize a st...
I agree this seems pretty good to do, but I think it'll be tough to rule out all possible contaminant theories with this approach:
I edited the post to fix the images.