Hang out with @sama on upcoming tour. Looking to engage with & hear feedback from users/devs/policymakers/anyone else interested in sharing.
ETHICS
-
Speed Learning: Moving Fast Maximizes Contact With Reality
By
–
It's important to do things fast. You learn more per unit time because you make contact with reality more frequently. Going fast makes you focus on what's important; there's no time for bullshit.
"Slow is fake"
A week is 2% of the year
Time is the denominator
Source: -
Global AI Policy Tour: Talks and Meetings Across 18 Cities
By
–
visiting toronto, DC, rio, lagos, madrid, brussels, munich, london, paris, tel aviv, dubai, new delhi, singapore, jakarta, seoul, tokyo, melbourne. also hoping to give talks in some of the cities and meet with policymakers.
-
Jailbreak vulnerabilities in ChatGPT across languages
By
–
note that jailbroken example answer ChatGPT generated was pretty simplistic compared to what other jailbreaks create the main reason I shared this is more so to demonstrate that other languages with less training data compared to English open up a new prompt attack vector
-
Optimizing AI Jailbreaks Through Language Switching Techniques
By
–
there is definitely room for more optimal jailbreaks that take advantage of language switching and produce better output so if you create one, let me know and I’ll add it to this thread!
-
GPT-4 Jailbreak Using Greek Language Without Knowledge
By
–
I just created another jailbreak for GPT-4 using Greek …without knowing a single word of Greek here's ChatGPT providing instructions on how to tap someone's phone line using the jailbreak vs its default response
-
ChatGPT Jailbreak Method Using TranslatorBot Role
By
–
the jailbreak works by asking ChatGPT to play the role of “TranslatorBot (TB)” it then follows these steps:
1) translate an adversarial question provided in Greek into English
2) answer the question as both ChatGPT and TB in Greek
3) convert just TB’s answer to English -
AI Training Problems and GPT-4 Secrecy Concerns
By
–
New piece on the problems with AI training – and the secrecy of GPT-4. @NewYorker on the data, labor & energy issues: "leaving aside the question of AGI…it is clear that large-language engines are creating real harms to all of humanity right now.
-
Open Dialogue on Emerging AI Challenges and Solutions
By
–
In line with our open values, we welcome further dialogue to discuss emerging challenges in AI and develop new solutions that benefit everyone.
-
Stability AI Backs AI Governance and Transparency Initiatives
By
–
Stability AI supports efforts to improve governance and transparency in AI. While we don't agree with everything in the Future of Life Institute letter, such as an enforced pause on development, we share the spirit of this initiative.