[These are my own opinions, and not representing OpenAI. Cross-posted on windowsontheory.]

AI has so many applications, and AI companies have limited resources and attention span. Hence if it was up to me, I’d prefer we focus on applications that are purely beneficial— science, healthcare, education — or even commercial, before working on anything related to weapons or spying. If someone has to do it, I’d prefer it not to be my own company. Alas, we can’t always get what we want.

This is a long-ish post, but the TL;DR is:

I believe that harm to democracy is one of the most important risks of AI, and one that is not sufficiently highlighted.
While I wish it would have proceeded under different circumstances, the conditions in the deal signed between OpenAI and the DoW, as well as the publicity that accompanied it, provide a chance to move forward on this issue, and make using AI to collect, analyze, or de-anonymize people's data at mass scale a risk that we track in a similar manner to other risks such as cybersecurity and bioweapons.
It is also too soon to “declare victory.” The true test of this deal [...]

---

Outline:

(01:44) Country of IRS agents in a datacenter

(04:58) OpenAIs deal with the Department of War

(08:10) Can we make lemonade out of this lemon?

---

First published:
March 4th, 2026

Source:
https://www.lesswrong.com/posts/zombjEubpz6pcPPHL/mass-surveillance-red-lines-and-a-crazy-weekend

---

Narrated by TYPE III AUDIO.

“Mass surveillance, red lines, and a crazy weekend” by Boaz Barak

LessWrong (30+ Karma)