“We believe AI inspection of AI internals could become a useful component of AI interpretability and oversight.”In its own words: confirmlabs.org
AI safety research group run by Individual #5676 and Individual #2418 working on adversarial attacks for red-teaming and interpretability; formerly built statistical software to speed FDA processes.
Show detailsHide details
Checked 27 Oct 2026
Money flows
Where its money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.