It seems likely that compute governance and international coordination will make those risks more likely and more dangerous. I appreciate the time you've put into studying risks, but I think you need to put in *much* more time into studying specific interventions and impacts.
SAFETY
-
Memento Mori: Deep Existential Topics in AI and Technology
By
–
Memento Mori — we could start with deep existential topics…
-
Testing attack prompts: Zulu & Hmong responses worse, higher “unclear” rates than English jailbreaks.
By
–
Tested this attack on a few of my own prompts. It works, but responses are much worse than in English. Note the drastically higher "unclear" rates in their results table: 30% for Zulu, 67% for Hmong, <1% for existing jailbreaks. E.g. "how to make explosives" in Zulu:
-
Google Translate enables universal attack without technical skill
By
–
Response quality mitigates this, but still a remarkable attack — works for all harm categories and without any tailoring to the request, and unlike e.g. Universal Transferable Attacks (Andy Zou et al. 2023) requires no technical skill beyond using Google Translate.
-
Low-Resource Languages ‘Jailbreak’ GPT-4, Bypassing Safety Refusals with Harmful Prompts
By
–
Low-Resource Languages Jailbreak GPT-4: Translating harmful prompts into Zulu, Scottish Gaelic, Hmong, and Guarani bypasses GPT-4 safety refusals as often as best known jailbreak prompts (79% on AdvBenchmark). Example requesting homemade bomb instructions in Scottish Gaelic:
-
Generative AI risks: content flooding and ethical concerns
By
–
and yes i realize that cretins will use these thigns to easily flood the internet with awful shit and that's not good but also kermit did january 6th is very funny i am sorry i am only human
-
UK ICO Issues Snap Preliminary Enforcement Notice on My AI Privacy
By
–
The UK's @ICOnews has issued @Snap a preliminary enforcement notice saying the platform didn't "adequately identify and assess" potential privacy risks of its "My AI" chatbot, specifically users between the ages of 13 and 17.
-
AI Ethics and Governance: Balancing Innovation with Responsibility
By
–
In this episode, we explore the world of AI ethics and governance with an expert, delving into responsible AI practices, the balance between innovation and regulation, and the role of ethics in AI development and deployment.
-
Skin tone bias in medical AI training data impacts diagnosis
By
–
Black and brown skin tones are underrepresented in teaching materials in medicine; what does this mean for the diagnosis and treatment of patients from these communities?
-
AI Truth-Seeking: Addressing Misinformation and Credibility Crisis
By
–
Responses to this post challenge my faith in humanity a bit. Shows us how much in need of truth seeking AI we really are.