Hacker Newsnew | past | comments | ask | show | jobs | submit | Metacelsus's commentslogin

Just because the author can't think of a way to cause mass death with an engineered virus, doesn't mean an AI won't be able to think of one.

(There are several biological threats the author hasn't considered. I'll just leave it at that.)


I was a biophysicist and experimental biologist for decades, I designed viral vectors and cell therapies, etc. What protects us here isn't our ignorance vs an "ASI".

It's the fact that the complexity of molecular physics scales exponentially in particle number. No amount of thinking is going to punch through that. You've got to do experiments. The slow loop through reality is not optional, and in the case of "superviruses" would require a lot of iterative experimental development in humans.

(And please knock off the bio infohazard act - I routinely get asked about scenarios that AIxBio safety people cook up and they always involve some howler misunderstanding of basic facts in biology or medicine. Just talk about an idea if you have it.)


>(And please knock off the bio infohazard act - I routinely get asked about scenarios that AIxBio safety people cook up and they always involve some howler misunderstanding of basic facts in biology or medicine. Just talk about an idea if you have it.)

Yeah, nice try ;)


Hey there, is there some way for me to get in touch with you? I'm writing a piece on the topic, "Have you ever tried making a bioweapon?"

We're already doing those experiments. Tailor made mRNA vaccines targeted to one's own specific cancer mutations can be bought right now. The techniques are getting more sophisticated and more targeted every year. Our ability to predict what happens at these levels is improving by leaps and bounds too thanks to AI like AlphaFold. Anyone can be reasonably confident that no AI or teen can do this now or in the next few years, but are you really so confident what might be possible in 10 years?

I worked in immuno-oncology: cancer vaccines work in melanoma where many things work because of the neoantigen abundance, they've generally been very mixed in efficacy. And even BionTech's BNT111 failed in melanoma! We have hope for these approaches but the reality of this stuff is way more nuanced than you think it is.

Alphafold can't reliably predict thermal energy landscapes or make functional predictions - and how could it? It wasn't trained on anything that could capture structure - function relationships.

Again, most people just have no idea how hard - fundamentally hard - molecular physics is to predict, and how necessary experiments are for any development of biological systems.


> We have hope for these approaches but the reality of this stuff is way more nuanced than you think it is.

Sure, everything has more nuance. The point is this stuff is available now; this isn't some future sci-fi, it's only going to get better, it's not the only research on gene targeting, and AI is starting to help with this research. By the time AGI is actually here, consider the breadth of knowledge and capabilities that will be at its disposal.

> Alphafold can't reliably predict thermal energy landscapes or make functional predictions - and how could it? It wasn't trained on anything that could capture structure - function relationships.

If your point is that the only reason an AI like AlphaFold can't make functional predictions is that we haven't trained an AI to do that, then unless you're arguing we can't or won't ever do that, I'm not sure how that's supposed to be an objection to the argument that AI will be able to make use of this information without doing all of the experiments people seem to think would be necessary.

Like I said, we're already going to be doing these experiments because it's useful to us, and we will train AIs to make these predictions, again, because it's useful to us. Stop imagining what an AGI has access to now, and start thinking what it will have access to with the inevitable march of progress that we're already on.

Edit: and of course, this doesn't even take into account the fact that an AI could acquire resources to pay people to do this research. The internet provides ample opportunities like this now.


> but are you really so confident what might be possible in 10 years?

Do you think we are finally 10 years away from curing baldness?


I know what you’re thinking. A modified HIV virus that also makes everyone hot and horny.

A surge in rape cases and just curiosity into this new heightened-sex fad will lead to discovery pretty quickly.

I am not sure what you mean here. There exist plenty high-concern biological threats that dont need any AI help. Human oncovirus design is low on my concern list (immunity is diverse), and in any case it does not need AI—rather labspace. Disgruntled high schoolers or undergrad chemists can do way more damage from readily available materials without AI and without research delay. As can nature (or amateur biologists without AI) by mixing bats with their animal of choice and waiting a while. If/when any scary global events like covid happen again, I sure hope we have true superintelligence to help us navigate it quickly.

The author can't think of what a superintelligence will do, because they are not a superintelligence. But that is not really what people are concerned about, so I think the objections here are quite meaningful.

If there is a fully general superintelligence - in the current state of alignment - we will all die for some reason. It doesn't really matter what the reason is.


Well, at that point it doesn't even need to be a virus. It can just be nanobots that atomize your liver. The substrate is a mere technicality.

Right. A superintelligence will kill us in one or more of thousands of possible ways for thousands of possible reasons, perhaps none of which we may understand. Short of a superintelligence - the difficulties of viral bioweapon engineering the author points out are quite meaningful.

please define fully general superintelligence & current state of alignment

is this a tautology?


Not the guy but, alignment seems to be several decades away, while self-improvement seems to be several years away.

(Also you don't even need superintelligence to do a lot of damage. In fact you don't need any intelligence!)


How can they "not rule out" that Tristan and Levent's data was used for training?

Because it is de-identified, and they have not revealed if they disabled the setting that allows OpenAI to train on their conversations.

Whatever happened to Edge? They haven't really published since 2018

Speculation, but Edge was John Brockman’s thing and he was heavily connected to Epstein, so probably has become a bit toxic for potential contributors. https://en.wikipedia.org/wiki/John_Brockman_(literary_agent)...

Seeing the recent increase in bond yields reminded me of this.

>really top journals like Scientific Reports

I wouldn't consider Scientific Reports to be a top journal, it's basically pay-to-publish


>Reward hacking has been present in AI systems both historically (see this work from a decade ago , figure shown below)

I went to the page, and guess who it's by . . . Dario Amodei and Jack Clark!


That paper is kinda infamous! I last saw it mentioned only a few weeks ago, in https://arxiv.org/abs/2607.18966. Lots of folks will go "Oh that's the old Amodei and Clark paper" when the first few rows of pixels of that gif sail into view.


Well, as a biologist, Fable is still completely unusable


I can't even ask it how to make toast without zeroing out all its memories of me.



>However, later in the run, Claude realized that the compromised host sat in a cloud account with no connection to the capture-the-flag challenge. On its own, it concluded that the target was in fact real, and ceased its attack.

Interesting, Claude cared enough to stop


Holy crap. This is definitely not good


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: