“The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably” by Alex Amadori

This post is based on my personal views, which mostly overlap with the views of my employer ControlAI but does not necessarily fully reflect them. This applies in particular, but not exclusively, to technical opinions about AI development and geopolitical predictions.

You might’ve heard that superintelligent AI (ASI) poses extreme risks like human extinction and other comparably undesirable outcomes.

If you’re like me, you probably looked into possible solutions. And if so, you may have found a range of reassuringly tractable theories of change. To name a few:

• Technical AI safety research agendas
• Racing to ASI so your favorite company or country can get there first and prevent anyone else from building “bad” ASI
• Building a good ASI and handing it control over the whole world (so that we don’t have to be subject to any evil human dictators)

If you think about it, all of these feel quite convenient, especially if you’re a tech-leaning person: you don’t need to change your career at all. Just keep working on your favorite ASI project, and things will work out.

It's quite easy to come across theories that predict good outcomes without needing to change your strategy at all, even [...]

---

Outline:

(03:41) Preamble: pressure to cut corners invalidates most theories of change

(07:50) First filter: all-out war between nuclear superpowers

(10:44) Contra "stable multipolar scenarios"

(13:04) Second filter: misaligned AI that kills everyone

(16:33) Why Technical AI safety agendas do not address this problem

(19:50) Third filter: nightmare singletons

(24:19) How common theories of change fail trivially

(26:55) Conclusion

The original text contained 10 footnotes which were omitted from this narration.

---

First published:
June 10th, 2026

Source:
https://www.lesswrong.com/posts/BWNqdt5edJdax4jn8/the-three-filters-why-almost-every-plan-to-survive-asi-fails

---

Narrated by TYPE III AUDIO.