Pick one verification mechanism, such as network taps, trusted execution environments, chip telemetry or satellite monitoring, and write a short, clear analysis of how it works and how it could fail.
International agreements on AI are only as good as our ability to check them. Very few people understand these mechanisms; good explainers help policymakers and new researchers.
Output: A 2,000-word shallow dive in the style of Lennart Heim’s blog.
Read the summary of “Six Layers of Verification” and pick one mechanism.
Read two or three of the specific papers on it from the verification reading list.
Explain: what it checks, what it needs to be trusted, how a cheater might evade it, and how mature it is.
Add a simple diagram.
Ask someone technical to check it, then publish.
All steps done
Share what you made, then try another project. The PDF version has room for notes.
MIRI TGT published a draft international agreement to prevent premature superintelligence. Pick one article and ask: how would it be verified, enforced and evaded?
Why do so many governance proposals focus on chips? Read one key paper and write a jargon-free explainer for someone outside tech.
Pick a known AI cluster from Epoch AI’s GPU cluster data, find it in free satellite imagery and document how it has grown over time.
