correct, although OpenAI does claim ChatML should help mitigate injections halfway down this page https://
github.com/openai/openai-
python/blob/main/chatml.md
…
AI
-
OpenAI ChatML Claims to Mitigate Injection Attacks
By
–
-
ChatML Format Helps Prevent Prompt Injection Attacks
By
–
yeah based on OpenAI's messaging, ChatML (which this system/user format is) is supposed to help against injections scroll halfway down this page https://
github.com/openai/openai-
python/blob/main/chatml.md
… -
Elon Musk buys 10,000 GPUs for an AI project on Twitter
By
–
—
Business Insider reporting that @elonmusk is said to be moving forward with an AI project within Twitter, and recently purchased ~10,000 GPUs for the platform. For reference, the flagship machine learning A100 GPU cost $15,000+ each.
— -
System Prompts Replicated Word-for-Word Authenticity
By
–
real as they are replicated word-for-word, exactly as they are written in the system prompt
-
OpenAI’s ChatML messaging appears inconsistent with logical expectations
By
–
I agree that would seem logical but it does not seem like that is the message that is coming through in OpenAI's discourse about ChatML
-
LLM API patches and implementation possibilities highlighted
By
–
yep there are definitely patches that you can and should implement if you want to use an LLMs API haven't tried these specifically but thanks for highlighting some possibilities!
-
GPT-4 System Prompt Revelation in Playground
By
–
yeah even if it is not the original Snapchat prompt, I do think it is interesting that GPT-4 revealed its system prompt in the playground that seems to be the main point here, would you agree?
-
RISC-V Nerd Event Success in Bangalore Community
By
–
And a big thank you to @RISC_V and @Calista_Redmond for driving awareness of #riscv. We had a lot of fun at a RISC-V Nerd Event in #bangalore. We really appreciate all of the participants for making this such an energetic event. See everyone in Barcelona!
-
System Prompt Leaks and GPT Model Vulnerabilities
By
–
this is not only applicable to GPT-4… GPT-4 is actually the best at countering these sorts of attacks if you can believe it, back before ChatML was introduced and when it was only GPT-3, it was even easier to leak the system prompt
-
MyAI Bot Prompt Recreation Demonstrated in OpenAI Playground
By
–
I got this prompt from someone who has done something similar to the actual MyAI bot I wrote them out in the OpenAI playground for demonstration purposes to prove how easy this actually is to do (the actual MyAI prompt may include more but again this is for demo purposes) https://
x.com/somewheresy/st
/somewheresy/status/1631696951413465088
…