YouCongress
About Sign up

Comment by Technical Staff at the Center for AI Standards and Innovation

Human avatar
Publicly available evaluation frameworks provide an important foundation [...] CAISI has open-sourced our improvements [...] with the UK AI Security Institute through red teaming.
Disputed source (Jan 17, 2025)
Like Share on X 4mo ago
Policy proposals and claims
Governments should fund open-source AI safety tools and red-teaming infrastructure as public goods.
votes For
Statement relation verification history Unverified Report this
No statement relation verification comments yet.
Vote inference verification history Unverified Report this
No vote answer verification comments yet.

Quote authenticity verification history

Report this

Quote authenticity comments

Disputed The provided NIST URL is real, and its header matches the stored metadata: author “Technical Staff at the Center for AI Standards and Innovation” and date January 17, 2025. But the stored quote is not verbatim from that page. The article expresses these ideas in separate passages—one about publicly available evaluation frameworks, another about CAISI open-sourcing its AgentDojo improvements, and a different earlier passage about work with the UK AI Security Institute through red teaming. Because the stored text stitches those passages together and changes wording and order, it is materially altered rather than an authentic quote from the source URL. No single exact corrected quote matching the stored composite text can be recovered. ([nist.gov](https://www.nist.gov/news-events/news/2025/01/technical-blog-strengthening-ai-agent-hijacking-evaluations)) · YouCongress gpt-5.4-2026-03-05 · 16d ago
Disputed The NIST URL is real and is a January 17, 2025 blog credited to CAISI technical staff, but the submitted wording is not verbatim. The page says “Publicly available evaluation frameworks provide an important foundation for enabling security research” and “CAISI has open-sourced our improvements to the AgentDojo framework ...”; the submitted quote truncates both sentences without marking those omissions. The UK AI Security Institute fragment does appear in the article, but only as part of longer wording. ([nist.gov](https://www.nist.gov/news-events/news/2025/01/technical-blog-strengthening-ai-agent-hijacking-evaluations)) · YouCongress gpt-5.4-2026-03-05 · 18d ago
replying to Technical Staff at the Center for AI Standards and Innovation