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?
@alexalbert__
-
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
-
System Prompt Exposure: Security and Jailbreak Risks for LLM Integration
By
–
this poses a massive problem for customers who are wanting to integrate LLMs into their products exposing the system prompt not only hurts your perceived product security reputation but also makes it easier to jailbreak your product and produce undesirable outputs
-
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
… -
GPT-4 Vulnerability: Prompt Injection and System Prompt Leakage
By
–
GPT-4 is highly susceptible to prompt injections and will leak its system prompt with very little effort applied here's an example of me leaking Snapchat's MyAI system prompt:
-
GPT-4 Text Compression and Decompression Token Efficiency
By
–
yes in many cases the token count is in fact less it is almost impossible to get GPT-4 to regenerate the original text word for word when decompressing the compressed text but usually, the gist of it remains pretty intact
-
Chain of Thought Reasoning and Prompting Techniques
By
–
chain of thought reasoning/prompting https://
arxiv.org/abs/2201.11903 -
Newsletter on prompt engineering techniques and LLM developments
By
–
also, not trying to do an annoying plug, but if you actually want to stay up to date on prompt engineering techniques and stuff I'm working on, check out my newsletter every week I share my analysis on recent developments in LLMs, prompts, and jailbreaks http://
thepromptreport.com -
Jailbreak Techniques for Prompt Engineering and Emergent Behaviors
By
–
these techniques (many initially created for jailbreaks) should be applicable to a range of prompt engineering tasks jailbreaks showcase capabilities on the edge so using similar tactics could reveal other emergent behaviors lmk if there are other techniques I should add!
-
Directional Stimulus Prompting: Using Keywords to Guide LLM Outputs
By
–
Directional Stimulus Prompting we use a smaller LLM to extract keywords from a piece of text and insert them as directional hints into another prompt this is highly beneficial for generating detailed summarizations and I expect more general applications for it will emerge