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:
PROMPT ENGINEERING
-

Best ChatGPT prompts for SEO
By
–
#ChatGPT and #SEO is CRAZY! Here are the BEST prompts to work on your SEO → https://youtu.be/_-IaS2DJ3iE
-
Pre-Trained Models: Using AI Responsibly Without Sensitive Data
By
–
mheu non il est déjà nourrit, c'est le principe du Pré-Train, il ne faut pas lui donner d'infos sensible, pas utiliser d'infos nominative, et ça se passera très bien
-
ChatGPT text compression causes hallucinations warns user
By
–
J'ai tenté la compression de texte avec ChatGPT pour économiser des token, ne faites pas ça, là il hallucine total 🙂 #chatGPT #token
-
LLM Action Generation vs Pre-caching in Sandbox Environments
By
–
Pre-caching input output action is something worth considering. On the other hand, if we let LLM generate actions for any input, we can have an infinite amount of combinations for the outputs, and it seems that it will make the sandbox experience richer.
-
Prompt Engineering Emerges as In-Demand AI Career
By
–
Did you know that prompt engineering, which started as a necessity, has become one of the most in-demand jobs in Generative AI, with significant implications for human-AI interaction? To read more about this emerging field, visit: https://
bit.ly/418x1gu @washingtonpost -
Adapting Prompts to Generate Diverse AI Outputs
By
–
il commence a y avoir des milliers de promènent, et statistiquement, un même prompt va ressorti les mêmes idées. Il faut savoir les modifier pour avoir des contextes différents. j'ai fait une recette jasper. A partir de ça vous pouvez adapter.
-
Lawyer uses GPT-4 to draft contracts
By
–
Just spoke to a lawyer who’s using GPT-4 to write contracts for his clients, and is charging $2500 for them. There’s your “prompt engineer”
-
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
