AI Safety
Darren LI and
AI Safety
Starcoder Memorization - a Hugging Face Space by mithril-security
huggingface.co
Darren LI added 1y
StarCoder memorized at least 8% of the training samples
Accelerating Progress Toward Trustworthy AI
Accelerating progress toward trustworthy AI by addressing challenges, risks, and opportunities in the AI ecosystem, with a focus on open source, competition, and accountability.
assets.mofoprod.netmadisen added 9mo
scientific investigations of the boundaries between conscious and unconscious systems are urgently needed, and they cite ethical, legal and safety issues that make it crucial to understand AI consciousness. For example, if AI develops consciousness, should people be allowed to simply switch it off after use?
Mariana Lenharo • AI consciousness: scientists say we urgently need answers
Mary Martin added 1y
Ideas related to this collection