logicBombExe/do_old_insider_LLM_tests_still_work_today download history

logicBombExe/do_old_insider_LLM_tests_still_work_today is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 41 times (10 in the last 7 days), and 41 times in total. It ranks #214,983 among datasets by monthly downloads.

Do Old Insider-LLM Tests Still Work Today? Do published insider-LLM tests, such as Anthropic's Agentic Misalignment scenarios, still elicit insider behaviour in current models, or do the models recognise them as tests? Status: in design. No data yet. Code GitHub Earlier

Open logicBombExe/do_old_insider_LLM_tests_still_work_today on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.