Posts

Boring & straightforward trauma explanation 2024-11-08T09:45:19.486Z
Any real toeholds for making practical decisions regarding AI safety? 2024-09-29T12:03:08.084Z
How to hire somebody better than yourself 2024-08-28T08:12:53.450Z
Parasites (not a metaphor) 2024-08-08T20:07:13.593Z
aimless ace analyzes active amateur: a micro-aaaaalignment proposal 2024-07-21T12:37:39.925Z
New fast transformer inference ASIC — Sohu by Etched 2024-06-26T09:56:08.649Z
If you are also the worst at politics 2024-05-26T20:07:49.201Z
shortest goddamn bayes guide ever 2024-05-10T07:06:23.734Z
Is being a trans woman (or just low-T) +20 IQ? 2024-04-24T20:04:36.829Z
Speedrun ruiner research idea 2024-04-13T23:42:29.479Z
Upcoming unambiguously good tech possibilities? (Like eg indoor plumbing) 2024-04-11T23:14:06.355Z
Any evidence or reason to expect a multiverse / Everett branches? 2024-04-09T05:26:30.990Z
Best *organization* red-pill books and posts? 2024-03-20T07:01:16.536Z
Fixed point or oscillate or noise 2024-03-14T18:37:11.212Z
Let's build definitely-not-conscious AI 2024-03-06T07:50:01.880Z
What's this 3rd secret directive of evolution called? (survive & spread & ___) 2024-02-07T14:11:58.143Z
Wrong answer bias 2024-02-01T20:05:38.573Z
The economy is mostly newbs (strat predictions) 2024-02-01T19:15:49.420Z
What exactly did that great AI future involve again? 2024-01-28T10:10:21.270Z
Decent plan prize winner & highlights 2024-01-19T23:30:34.242Z
Decent plan prize announcement (1 paragraph, $1k) 2024-01-12T06:27:44.495Z
Go flash blinking lights at printed text right now 2023-11-05T07:29:44.630Z
Responsible scaling policy TLDR 2023-09-28T18:51:20.330Z
Series of absurd upgrades in nature's great search 2023-09-03T09:35:20.760Z
We can do better than DoWhatIMean (inextricably kind AI) 2023-08-19T05:41:47.046Z
Could fabs own AI? 2023-08-19T00:16:37.848Z
Could we breed/engineer intelligent parrots? 2023-08-02T07:32:17.686Z
When did you orient? 2023-06-19T07:22:27.968Z
Work dumber not smarter 2023-06-01T12:40:31.264Z
When should I close the fridge? 2023-05-17T16:56:35.629Z
Distinguishing misuse is difficult and uncomfortable 2023-05-01T16:23:17.040Z
More money with less risk: sell services instead of model access 2023-03-04T20:51:36.480Z
Planning capacity and daemons 2022-09-26T00:15:42.409Z
Inner alignment: what are we pointing at? 2022-09-18T11:09:58.661Z
AI-assisted list of ten concrete alignment things to do right now 2022-09-07T08:38:29.757Z
Do yourself a FAVAR: security mindset 2022-06-18T02:08:47.415Z
Against unstoppable crypto prediction markets 2021-02-25T06:02:23.102Z
lemonhope's Shortform 2020-01-27T00:52:37.833Z
Creating Environments to Design and Test Embedded Agents 2019-08-23T03:17:33.265Z

Comments

Comment by lemonhope (lcmgcd) on Frontier AI systems have surpassed the self-replicating red line · 2024-12-11T03:40:18.326Z · LW · GW

I am glad to see somebody make the point properly. It's a weird state of affairs. We know the models can implement PoCs for CVEs better than most coders. We know the models can persuade people pretty effectively. Obviously the models can spread and change very easily. It's also easy for a rogue deployment to hide because datacenter GPUs draw 70W idle and update scripts constantly use tons of bandwidth. There's just no urgency to any of it.

Comment by lemonhope (lcmgcd) on Alternatives to Masks for Infectious Aerosols · 2024-12-09T18:06:39.647Z · LW · GW

How do you measure results?

Comment by lemonhope (lcmgcd) on Alternatives to Masks for Infectious Aerosols · 2024-12-08T16:53:36.832Z · LW · GW

If you wanted to take this idea to an absurd level, you could install a dropped ceiling made partially of furnace filters, and a grid of fans above it. Maybe have the outer perimeter of fans blowing up and the inner area blowing down, to try to get one large convection through the entire room.

Comment by lemonhope (lcmgcd) on Alternatives to Masks for Infectious Aerosols · 2024-12-08T16:44:35.999Z · LW · GW

How do you figure out the optimal filter thickness? If you hypothetically had a very weak fan then it wouldn't push much air through even furnace filters. If you had a magic constant air flow source then you would want the thickest filter possible.

I guess I am just wondering if you could use something better-looking and cheaper, like semi-transparent paper with lights behind it or a washable sheet/tapestry.

Comment by lemonhope (lcmgcd) on Alternatives to Masks for Infectious Aerosols · 2024-12-08T14:54:51.903Z · LW · GW

Have you heard of Big Ass Fans? It's a company that makes what you would expect. Do you think your ceiling fan filter could work with a 30ft fan?

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-12-07T00:16:44.536Z · LW · GW

What is the current popular (or ideally wise) wisdom wrt publishing demos of scary/spooky AI capabilities? I've heard the argument that moderately scary demos drive capability development into secrecy. Maybe it's just all in the details of who you show what when and what you say. But has someone written a good post about this question?

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-24T17:10:13.357Z · LW · GW

Einstein started doing research a few years before he actually had his miracle year. If he started at 26, he might have never found anything. He went to physics school at 17 or 18. You can't go to "AI safety school" at that age, but if you have funding then you can start learning on your own. It's harder to learn than (eg) learning to code, but not impossibly hard.

I am not opposed to funding 25 or 30 or 35 or 40 year olds, but I expect that the most successful people got started in their field (or a very similar one) as a teenager. I wouldn't expect funding an 18-year-old to pay off in less than 4 years. Sorry for being unclear on this in original post.

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-21T13:12:13.050Z · LW · GW

I don't have a witty, insightful, neutral-sounding way to say this. The grantmakers should let the money flow. There are thousands of talented young safety researchers with decent ideas and exceptional minds, but they probably can't prove it to you. They only need one thing and it is money.

They will be 10x less productive in a big nonprofit and they certainly won't find the next big breakthrough there.

(Meanwhile, there are becoming much better ways to make money that don't involve any good deeds at all.)

My friends were a good deal sharper and more motivated at 18 than now at 25. None of them had any chance at getting grants back then, but they have an ok shot now. At 35, their resumes will be much better and their minds much duller. And it will be too late to shape AGI at all.

I can't find a good LW voice for this point but I feel this is incredibly important. Managers will find all the big nonprofits and eat their gooey centers and leave behind empty husks. They will do this quickly, within a couple years of each nonprofit being founded. The founders themselves will not be spared. Look how the writing of Altman or Demis changed over the years.

The funding situation needs to change very much and very quickly. If a man has an idea just give him money and don't ask questions. (No, I don't mean me.)

Comment by lemonhope (lcmgcd) on Project Adequate: Seeking Cofounders/Funders · 2024-11-17T08:03:45.188Z · LW · GW

Wasted opportunity to guarantee this post keeps getting holywar comments for the next hundred years.

Comment by lemonhope (lcmgcd) on Project Adequate: Seeking Cofounders/Funders · 2024-11-17T08:02:34.707Z · LW · GW

This is pretty inspiring to me. Thank you for sharing.

Comment by lemonhope (lcmgcd) on Shortform · 2024-11-17T07:30:03.098Z · LW · GW

The other day I was trying to think of information leaks that a competent conspiracy couldn't prevent, regarding this. I just thought of one small one: people will sometimes randomly die or have their homes raided. If the slavery is common, then sometimes the slaves will be discovered during these events. Even if the escapees wanted to silence the story out of shame, cops would probably gossip to the press.

So you can probably tally such events, crunch the numbers, and get a decent conspiracy-resistant estimate.

Comment by lemonhope (lcmgcd) on Alexander Gietelink Oldenziel's Shortform · 2024-11-17T07:07:14.530Z · LW · GW

As a layman, I have not seen much unrealistic hype. I think the hype-level is just about right.

Comment by lemonhope (lcmgcd) on Alexander Gietelink Oldenziel's Shortform · 2024-11-17T07:05:18.755Z · LW · GW

You should not bury such a good post in a shortform

Comment by lemonhope (lcmgcd) on Which evals resources would be good? · 2024-11-17T06:54:32.230Z · LW · GW

Maybe it should be a game that everyone can play

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-17T06:30:45.708Z · LW · GW

Yeah I just wanted to check that nobody is giving away money before I go do the exact opposite thing I've been doing. I might try to tidy something up and post it first

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-16T04:44:45.063Z · LW · GW

Yes.

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-16T04:27:06.331Z · LW · GW

I do think I could put a good team together and make decent contributions quickly

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-11-16T04:13:38.295Z · LW · GW

I can only find capabilities jobs right now. I would be interested in starting a tiny applied research org or something. How hard is it to get funding for that? I don't have a strong relevant public record, but I did quite a lot of work at METR and elsewhere.

Comment by lemonhope (lcmgcd) on Should CA, TX, OK, and LA merge into a giant swing state, just for elections? · 2024-11-09T00:56:56.318Z · LW · GW

I wonder if anybody has tried to quantify how much it's worth to be a swing voter. I imagine if you are the government contractor up for renewal then it's worth quite a lot, but I wonder how much of the money/benefits the average Joe sees.

I don't know much about swing state benefits except that Milwaukee, Wisconsin got their lead pipes replaced by the fed and the workers were required to be local and they say they were paid quite well https://youtube.com/watch?v=4VpwgG0P8VU

Comment by lemonhope (lcmgcd) on The hostile telepaths problem · 2024-11-09T00:41:31.382Z · LW · GW

Aw man we used the same word for different things again

Comment by lemonhope (lcmgcd) on The hostile telepaths problem · 2024-11-09T00:37:33.648Z · LW · GW

Your examples fit the definition quite well. Apparently this is in the dictionary now. https://www.merriam-webster.com/dictionary/gaslighting

Comment by lemonhope (lcmgcd) on The hostile telepaths problem · 2024-11-08T08:47:46.592Z · LW · GW

Regarding this

Such as the moms in the abusive partners example above: each one could acknowledge her self-deception once it was safe for her abusive partner to know too. She got enough power (financial or social) to protect herself and her child, making the telepathic scan no longer a dire threat.

I would add that most abusive people don't really like crushing their loved ones and it is sometimes easy to get them to stop, eg by having a peer of the abuser get a private word with the two parties separately. I think it is common for there to be simple miscommunication/misunderstanding — the abuser does not typically actually benefit from the accusative situation.

Why haven't abuser & abusee already talked and figured this out? Well there is some force field where you can't have a normal conversation with someone who is hitting you (or you are hitting) about the hitting. Although I don't know how to put it in your terms here from this post.

Comment by lemonhope (lcmgcd) on The hostile telepaths problem · 2024-11-08T08:33:47.196Z · LW · GW

What gaslighting goes on in math class?

Comment by lemonhope (lcmgcd) on Should CA, TX, OK, and LA merge into a giant swing state, just for elections? · 2024-11-08T07:40:56.470Z · LW · GW

I am impressed with how far you thought this through. Amend the constitution, including the constitution amendment section

Comment by lemonhope (lcmgcd) on Should CA, TX, OK, and LA merge into a giant swing state, just for elections? · 2024-11-08T07:39:08.266Z · LW · GW

The opposing states in the coalition will simply declare war against the defectors. It's surely worth keeping your own army to keep being a swing bloc.

Comment by lemonhope (lcmgcd) on Should CA, TX, OK, and LA merge into a giant swing state, just for elections? · 2024-11-08T07:28:53.667Z · LW · GW

I want this to be a board game

Comment by lemonhope (lcmgcd) on Should CA, TX, OK, and LA merge into a giant swing state, just for elections? · 2024-11-08T07:26:55.158Z · LW · GW

I don't know if this would be good for the country, but it would certainly be good political entertainment.

Comment by lemonhope (lcmgcd) on The Sun is big, but superintelligences will not spare Earth a little sunlight · 2024-11-08T07:15:42.447Z · LW · GW

Doesn't everybody always code in a strong time-discount? I have never seen code without it.

Comment by lemonhope (lcmgcd) on The Sun is big, but superintelligences will not spare Earth a little sunlight · 2024-11-08T06:34:18.417Z · LW · GW

The o1 calculation is correct! https://math.stackexchange.com/a/1264753

.5 * (1 - sqrt(1.5e11^2 - 6.4e6^2)/1.5e11) = 4.55e-10

I am surprised. I have seen it mix up million and billion when calculating how many nukes the solar energy that hits earth is equivalent to.

Of course the sun is not nearly a point but whatever.

Comment by lemonhope (lcmgcd) on An alternative approach to superbabies · 2024-11-06T18:47:18.244Z · LW · GW

No good science without some good fun.

Comment by lemonhope (lcmgcd) on Representation Tuning · 2024-10-02T17:06:09.106Z · LW · GW

Wrong link? Looks like this is it https://arxiv.org/abs/2409.06927

Comment by lemonhope (lcmgcd) on Representation Tuning · 2024-09-29T17:14:51.764Z · LW · GW

Here is my understanding. Is this right?

 

Comment by lemonhope (lcmgcd) on Representation Tuning · 2024-09-29T17:10:09.137Z · LW · GW

Incredible!! I am going to try this myself. I will let you know how it goes.

honesty vector tuning showed a real advantage over honesty token tuning, comparable to honesty vector steering at the best layer and multiplier:

Is this backwards? I'm having a bit of trouble following your terms. Seems like this post is terribly underrated -- maybe others also got confused? Basically, you only need 4 terms, yes?

* base model
* steered model
* activation-tuned model
* token cross-entropy trained model

I think I was reading half the plots backwards or something. Anyway I bet if you reposted with clearer terms/plots then you'd get some good followup work and a lot of general engagement.

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-17T20:56:58.498Z · LW · GW

Hey!!! Thanks for replying. But did you or anyone you know consider chemical cisgenderization? Or any mention of such in the forums? I would it expect it to be a much stronger effect than eg joining the military. Although I hear it is common for men in the military to take steroids, so maybe there would be some samples there.... I imagine taking cis hormones is not an attractive idea, because if you dislike the result then you're worse off than you started.

(Oh and we were still together then. LK has child now, not sure how that affects the equation.)

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-16T20:36:07.661Z · LW · GW

Thank you! Seems like this bot works quite well for this task

Comment by lemonhope (lcmgcd) on Building an Inexpensive, Aesthetic, Private Forum · 2024-09-10T17:46:32.833Z · LW · GW

I have used a number of discourse forums and they just feel bad/wrong but I cannot explain why. I would also vote for more of an old-fashioned php BB with a nice theme. Those are always great, even though all my intuitions tell me they seem like they should suck. Shows how little I know.

Eg https://github.com/phpbb/phpbb

Also has styles: https://www.phpbb.com/customise/db/styles/board_styles-12?sid=6245508b90fd3410be19888406fae215

Basically I'm repeating what Said said

Comment by lemonhope (lcmgcd) on Amplify is hiring! Work with us to support field-building initiatives through digital marketing · 2024-09-10T17:39:41.460Z · LW · GW

If you have a clear metric to judge candidates on (eg engagement on a linkedin ad) then you might be able to do a super effective and quick performance-based hiring method. Shameless plug: https://www.lesswrong.com/posts/3AZkXwcCJZc5CAFQN/how-to-hire-somebody-better-than-yourself

Good luck!

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-10T17:30:24.948Z · LW · GW

Thanks for the cached explanation, this is similar to what I thought before a few days ago. But now I'm thinking that an older-but-still-youthful mouse would be better at avoiding predators and could be just as fertile, if mice were long lived. So the food & shelter might be "better spent" on them, in terms of total expected descendants. This would only leave the disease explanation, yes?

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-10T17:19:30.179Z · LW · GW

Where has the "rights of the living vs rights of the unborn" debate already been had? In the context of longevity. (Presuming that at some point an exponentially increasing population consumes its cubically increasing resources.)

Comment by lemonhope (lcmgcd) on Is being a trans woman (or just low-T) +20 IQ? · 2024-09-08T05:02:43.444Z · LW · GW

Hey thanks much for sharing new info with me. What a nice comment to read. I was sure someone would come by and be pissed and mean as hell, but folks have been engaging in quite good faith.

but I'm more reserved

I think this might point at the central problem with my evidence. People vary in how publicly they live their lives by orders of magnitude. It could be that only 1% of math geniuses are trans women but they post / get views on Twitter 100x more. Or a similar thing in high school and the workplace. Math professors tend to live quiet lives...

Anyway, unfortunately I think this post might be kinda too toxic/hurtful for the average reader to be worthwhile overall (although nobody has mentioned that to me) and I'll probably move it to a pastebin or something.

I think the basic question (whether hormones are fucking or helping your brain long-term) is quite important and deserves a better treatment. I might try to do that eventually.

Comment by lemonhope (lcmgcd) on What program structures enable efficient induction? · 2024-09-08T04:34:33.098Z · LW · GW

Any ideas?

Comment by lemonhope (lcmgcd) on Perhaps Try a Little Therapy, As a Treat? · 2024-09-08T04:23:10.654Z · LW · GW
Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-05T15:59:54.817Z · LW · GW

They keywords are much appreciated. That second link is only from 2022! I wonder if anybody suggested this in like 1900. Edit: some of the citations are from very long ago

Comment by lemonhope (lcmgcd) on lemonhope's Shortform · 2024-09-05T03:53:47.533Z · LW · GW

maybe you die young so you don't get your descendants sick

I've always wondered why evolution didn't select for longer lifespans more strongly. Like, surely a mouse that lives twice as long would have more kids and better knowledge of safe food sources. (And lead their descendants to the same food sources.) I have googled for an explanation a few times but not found one yet.

I thought of a potential explanation the other day. The older you get, the more pathogens you take on. (Especially if you're a mouse.) If you share a den with your grandkids then you might be killing them. Also, if several generations live together, then endemic pathogens stick with the clan much longer. This might eventually wipe out your clan if one of the viruses etc has a bad mutation.

If you die before your offspring even hatch then you might not pass them any pathogens. Especially if you swim a mile up a river that's dry 90% of the year. https://youtube.com/watch?v=63Xs3Hi-2OU This is very funny and 1 minute long.

Most birds leave the nest (yes?) so perhaps that's why there's so many long-lived birds.

Although IIRC, bats live a really long time and have a mountain of pathogens.

Anybody know if this explanation is fleshed out somewhere, or know a better explanation?

Comment by lemonhope (lcmgcd) on Anthropic is being sued for copying books to train Claude · 2024-08-31T04:55:07.808Z · LW · GW

Not that it matters, but the new version sounds kind of like the author is making a big deal, and the old version sounds like normal press language, to me at least

Comment by lemonhope (lcmgcd) on How to hire somebody better than yourself · 2024-08-29T14:54:46.221Z · LW · GW

Yeah I guess that's another prereq. I think you can make up for it some by having good work for people to do. I would rather work on a cool or valuable thing with amateurs than something lame with pros.

Comment by lemonhope (lcmgcd) on Meta: On viewing the latest LW posts · 2024-08-29T06:55:47.511Z · LW · GW

This is great!! I've just been using it now, thanks to your pointer.

Comment by lemonhope (lcmgcd) on One person's worth of mental energy for AI doom aversion jobs. What should I do? · 2024-08-29T06:54:51.916Z · LW · GW

I don't know if you're a woman, but the women I know have had much more success in politics than the men I know.

Comment by lemonhope (lcmgcd) on Day Zero Antivirals for Future Pandemics · 2024-08-29T06:43:05.578Z · LW · GW

Very valuable information! I have never heard of this artificial mucus stuff. Thank you for sharing.

Why do you want to go the FDA route? You think the gene therapy is the most promising?

Comment by lemonhope (lcmgcd) on On Interpters, Optimizing Compilers, and JIT · 2024-08-29T06:14:38.109Z · LW · GW

JITs are very underrated. Bad JavaScript code runs so much faster than bad C code. Sorry you got downvoted.