Aaron Scher
aaronscher.bsky.social
Aaron Scher
@aaronscher.bsky.social
Technical AI Governance Research at MIRI
Views are my own
Pinned
How can the US and China (or the international community, broadly) ensure compliance in AI agreements to manage large-scale risks? In a recent report, we discuss options available for verification of international AI treaties. Applicable to domestic rules too! 🧵 (1/12)
Mechanisms to Verify International Agreements About AI Development — MIRI Technical Governance Team
In this research report we provide an in-depth overview of the mechanisms that could be used to verify adherence to international agreements about AI development.
techgov.intelligence.org
Reposted by Aaron Scher
New AI governance research agenda from MIRI’s TechGov Team. We lay out our view of the strategic landscape and actionable research questions that, if answered, would provide important insight on how to reduce catastrophic and extinction risks from AI. 🧵1/10
techgov.intelligence.org/research/ai-...
May 1, 2025 at 10:28 PM
Reposted by Aaron Scher
MIRI's (@intelligence.org) Technical Governance Team submitted a comment on the AI Action Plan.

Great work by David Abecassis, @pbarnett.bsky.social, and @aaronscher.bsky.social

Check it out here: techgov.intelligence.org/research/res...
March 18, 2025 at 10:38 PM
One mechanism that seems promising is Flexible Hardware-Enabled Guarantees (FlexHEGs) and on-chip approaches. These could potentially be used to securely carry out a wide range of governance operations on AI chips, without leaking sensitive information. (1/3)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 5, 2024 at 8:01 PM
Reflection: The more I got into the weeds on this project, the harder verification seemed. Some difficulties are distributed training, algorithmic progress, and the need to be robust against state-level adversaries. It’s hard, but we have to do it! (1/1)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 5, 2024 at 7:59 PM
One mechanism that seems promising: Signatures of High-Level Chip Measures. Classify workloads (e.g., is it training or inference) based on high-level chip measures like power-draw, but using ‘signatures’ of these measures based on temporary code access. (1/6)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 4, 2024 at 7:57 PM
One mechanism that seems especially promising: Networking Equipment Interconnect Limits, like “Fixed Sets” discussed by www.rand.org/pubs/working... but can be implemented with custom networking equipment quickly. (1/8)
December 4, 2024 at 7:55 PM
One thread throughout this report is that low-tech, high-access solutions can often substitute for high-tech, low-access solutions, let’s walk through some examples. (1/12)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 4, 2024 at 7:51 PM
Distributed training (i.e., geographically distributed, decentralized) could pose major problems for many AI Governance plans. In the default case, large AI training happens in a small number of big data centers, so monitoring training can focus on those data centers. (1/10)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 4, 2024 at 7:49 PM
Inspectors who have full access to your systems seem like they could pose a major privacy and security risk, so it may be necessary to have very tight info sec around them, e.g., limited communication to home countries. (1/3)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 4, 2024 at 7:45 PM
Reflection: People I talked to had wildly different intuitions about the likelihood of direct US/China conflict in response to the threat of US AGI and ASI (superintelligence) development. (1/4)
I’ll be posting some snippets of interesting ideas from this giant verification report in other threads, linked here! (12/12)
December 4, 2024 at 7:45 PM
How can the US and China (or the international community, broadly) ensure compliance in AI agreements to manage large-scale risks? In a recent report, we discuss options available for verification of international AI treaties. Applicable to domestic rules too! 🧵 (1/12)
Mechanisms to Verify International Agreements About AI Development — MIRI Technical Governance Team
In this research report we provide an in-depth overview of the mechanisms that could be used to verify adherence to international agreements about AI development.
techgov.intelligence.org
December 4, 2024 at 7:43 PM
Alright here's a thread with some takes on recent AI safety-ish papers, written as I skim them because I want more content on this platform
November 24, 2024 at 5:58 PM