Li-Lian Ang

speaker

308 appearances 1 recordings 1 series first heard Apr 2026 last heard 2 Apr

Li-Lian Ang’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Apr 2026 with 1.

Appearances

newest first · ▶ plays the moment

Future of Life Institute Podcast · Defense in Depth: Layered Strategies Against AI Risk (with Li-Lian Ang) · 2 Apr 2026 podcast

Yeah, I'm not super sure.

Partly because there is a cost aspect to it in the sense of...

you want to be able to run these models and that might require, I guess, like what would be the cost factors involved in this?

Like one, there is an existing kind of like zero day, like a security vulnerability market that just kind of exists that people can exploit.

And then you need to like, you can like pay certain brokers or people who are like hackers online to be able to like find these vulnerabilities and try to exploit them.

But at the same time, there already exists many known vulnerabilities in many open source software.

And oftentimes, it's a matter of figuring out what are all the different vulnerabilities that do exist that haven't been patched yet, and how can you string them together?

And to me, the compute cost for this doesn't seem terribly high.

Or it isn't going to be in the millions.

It's probably...

too out of reach for like a non-state actor, the trouble will probably be with like actually trying to string together the complexity of all of these, like different zero days to actually have to mount a proper attack.

So I think like AI agents as they are today may not be able to uplift like to the point of like doing it autonomously.

But I think like every day they are

becoming more and more effective at doing this um such that like at some point um you may just be unlucky and they will like the right combination or like be able to like uh like find the right opportunity to be able to do this yeah yeah my intuition here is also just that this is a task like uh

I think they're good at finding patterns in large amounts of data.

That is their comparative advantage against people.

Um,

I think what has made AI agents a lot more powerful today than they were before is we have poured a lot more resources or a lot more training techniques into them being able to do the computations more effectively.

And if it's a matter of solving these puzzles, the better that we make their thinking processes

Showing 61–80 of 308 · page 4 of 16