> No, check https://en.wikipedia.org/wiki/Matsumoto_sarin_attack

That's a different attack. I'm talking about their 1993 anthrax attack: https://pmc.ncbi.nlm.nih.gov/articles/PMC3322761/

Analysis of the 48 suspect colonies confirmed them to be B. anthracis ... This genotype was identical to that of the Sterne 34F2 strain, used commercially in Japan to vaccinate animals against anthrax.

They used a vaccine strain because they didn't know any better. Even members of the elite can make mistakes, especially when operating outside areas they know well!

(This was not the only thing that went wrong, but several others were also knowledge failures.)

But even then, the debate isn't about whether open weight bioweapons exist today: it's about whether they will exist in the future. I think Amodei's argument here makes a lot of sense: "what I believe currently keeps us safe in biology is not 'defenders', or even the availability of materials, but a negative correlation between intellectual capability and desire to commit catastrophic harm. Previous technologies like internet search or even DNA synthesis were nowhere near powerful enough to break this correlation, but I worry that at its current rate of progress, AI will do so very soon."

(I'm not just spouting off; I put my time where my mouth is. I used to work in big tech, but I left for a much less well-paying job building an early-warning system for engineered pandemics.)

(Disclosure: I work at SecureBio, but not on the biological evals side.)

If you do end up making a technique demonstration video I'd love to see it!

Changing the kit without the assignment seems very much the right way to do it. No need to confuse your muscle memory.

Would it be ok if I wrote a blog post about your approach here, based on what you've written and shown? The general idea of playing drums with the feet is massively unexplored, and while I'd considered using bass pedals this way I didn't anticipate it was possible to get them working this well (which is part of why I went in a different direction).

This is fantastic! Do you have more videos of your foot-drumming? Or could you say more about how you do it? Are the pedals velocity-sensitive?

This is my setup: https://www.jefftk.com/p/making-a-pedalboard Four beaterless kick drum pedals. Another example in use https://www.youtube.com/watch?v=TcQLBfuaNqs

Not having tried it, I'd guess your setup is much more flexible, but requires much more work to provide a really steady beat on? And so would be a bit less well-suited to playing dance music (the main thing I do)?

That's a surprising claim: usually when I make this argument skeptics say that the knowledge barrier is so high that an LLM won't help enough!

I'd also be curious to hear what you think of the Aum Shinrikyo case, since that seems to me to be straightforwardly a failure of knowledge.

> The idea that all that's stopping some disaffected Joe sitting on his sofa at home and suddenly deciding to make a biological weapon is he can't get a set of instructions from ChatGPT is to miss the point.

I agree motivation is a huge barrier, in the sense that almost no one would do it. But to keep catastrophic bio attacks from happening as the knowledge barrier decreases it's not enough that most people wouldn't have the motivation. If 0.0001% of people have the motivation and 0.0001% have the means then we're probably ok, but if 0.0001% of people have the motivation and 0.1% have the means then we're not (0.0001% * 0.1% * population > 1).

It's not a matter of a one thing standing in the way of people making bioweapons: there's a long chain of actions one would need to complete, and many places for the chain to fail. Access to expertise can reduce the chance of failure at many of these steps, and AIs can increasingly substitute for human expertise: https://securebio.org/benchmarks/

> If you are motivated enough to assemble all the kit you'd need, and actually do it, then you should be motivated enough to find the knowledge to do it without chatgpt etc.

If someone was motivated enough to assemble the kit you need for anthrax and actually distribute it then you might expect them to also be motivated enough to find the knowledge to identify an appropriate strain, but in fact this is where Aum Shinrikyo failed in the 1990s: https://en.wikipedia.org/wiki/Aum_Shinrikyo#Incidents_before...

Lack of knowledge is one of many factors that can lead to failure, and LLMs make it less of a barrier.

> biological weapons are a terrible tool to do what most people want to do - which is target specific enemies

Except:

1. There are also people out there who want to kill everyone. They're sufficiently rare that no one with the motive has also had the means, but as technological progress keeps lowering the bar the risk of motive and means intersecting increases.

2. This didn't stop the Soviets. They did an enormous amount of very dangerous research with minimal logical application.

That doesn't seem right. I use these models as research assistants when writing lots of random blog posts (including in economically ~useless areas like the history of contra dance) and Fable 5 is a serious improvement (when I don't get downgraded!) over Opus 4.6-4.8 which was a serious improvement over Opus 4.

For some kinds of risk (ex: walking people through on how to make infectious bioweapons) an open-weights approach would increase risk.

I believe in the US this error correction has been discontinued in the East and in Texas, but is still done in the West for some kind of non-clock "inadvertent interchange" reasons I don't understand.