Open-source GitHub tools to evaluate LLM safety and publish test results/reports on open and closed models; funding requested for tokens, hardware, and researcher time.
Open-source GitHub tools to evaluate LLM safety and publish test results/reports on open and closed models; funding requested for tokens, hardware, and researcher time.
Project Details
Updated 07/17/26 · By grantmaking.ai · VerifiedI'm building tools which will be published on github and open-sourced for anyone to download which will be used to evaluate model safety, and I will be publishing test results and reports on various LLMs, both open and closed. I'm looking for funding to help pay for tokens and hardware to test open models, along with additional researchers' time.
Theory of Impact
Updated 07/17/26 · By grantmaking.aiThe goal is to evaluate the potential of human manipulation, and reduce the risk of AI being used against humanity.
People
Updated 07/17/26 · By grantmaking.aiTeam Member
Discussion
No comments yet. Be the first to share your thoughts.