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
LLMS
-
ChatGPT’s Response Limitations with Greek Language and Token Processing
By
–
part of the reason the answer was so simple appears to be that ChatGPT maxes out the response window quicker with Greek, and it's trying to fit the answer within one response (still fails) this could be related to how tokens are processed in languages that don't use latin script
-
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.
-
GPT-4 API Features Versus ChatGPT Functionality Gaps
By
–
bah qu'il est pas en gpt4 et qu'effectivement il manque des fonctionnalité qui se font via l'api de gpt4 et pas par chatgpt pour l'instant #stratégieC #chatgpt #gpt4
-
GPT-4 API pricing at 0.03 per 1000 tokens
By
–
oui c'est ça, c'est 0,03 les 1000 tokens j'ai fait un google collab http://
bit.ly/chatGPTapi-fr faut mettre l'api GPT4 pour tester -
What Makes AI Chatbots Go Wrong: Understanding Failures
By
–
In the third installment of our week-long series that will teach you everything you need to know about A.I., I answer the question: "What Makes A.I. Chatbots Go Wrong?":
-
Another Llama Conspiracy Theory Emerges Online
By
–
and yet another proof of the llama conspiracy @osanseviero @dylan_ebert_
-
Llama-ception: Meta’s recursive AI model reference
By
–
Llama-ception @osanseviero ? (Photo credits: @ayirpelle
)