SAFETY

→ View original post on X — @svenphilipsen

Sven Philipsen Signs Open Letter Calling to Pause Giant AI Experiments

By

@svenphilipsen

–

30 March 2023 7h56

I have signed the Open Letter to Pause Giant AI Experiments. https://
futureoflife.org/open-letter/pa
use-giant-ai-experiments/
… @FLIxrisk #ai #ArtificialIntelligence

→ View original post on X — @animaanandkumar

AI Safety Concerns Must Balance Progress and Guardrails

By

@animaanandkumar

–

30 March 2023 5h55

"Let us ban matrix multiplications for six months" is not a solution to dangers #AI potentially poses while ignoring vast benefits. As with any technology, I believe in humanity's ability to embrace positive benefits while figuring out safety guardrails. No need to stop progress

→ View original post on X — @gdb

OpenAI Mission: Ensuring AGI Benefits Humanity

By

@gdb

–

30 March 2023 2h07

Mission of OpenAI is to ensure AGI benefits all of humanity. Key ingredients we think will be important:

→ View original post on X — @sama

Three Essential Requirements for Safe AGI Future Development

By

@sama

–

30 March 2023 2h04

things we need for a good AGI future: 1) the technical ability to align a superintelligence
2) sufficient coordination among most of the leading AGI efforts
3) an effective global regulatory framework including democratic governance

GPT’s inability to unify concepts across languages enables jailbreaks

By

–

30 March 2023 0h44

imo this jailbreak highlights a unique lack of understanding of "unified concepts" by GPT if GPT analogously mapped concepts to entities regardless of language, it would be able to shut down my Greek adversarial prompt like it did when I asked the same prompt in English

Jailbreak vulnerabilities in ChatGPT across languages

By

–

29 March 2023 22h46

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

–

29 March 2023 22h46

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!

Closer Look at Jailbreak Chat Prompt Link

By

–

29 March 2023 22h46

you can take a closer look at the prompt here: http://
jailbreakchat.com/prompt/3e93895
c-2542-4201-a297-aa8be2db8bd7
…

GPT-4 Jailbreak Using Greek Language Without Knowledge

By

–

29 March 2023 22h46

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