The difference between a world that starts with 'Hi there! How can I assist you today?' and one that begins with 'Hello! Is there anything I can assist you with today?' would be quite peculiar.
PROMPT ENGINEERING
-
Democratizing AI and the Future of Prompt Engineering Discussion
By
–
Learn more about democratizing AI and the future of prompt engineering in our full discussion: https://
youtu.be/Y_NijxPgybo. -
MindStudio: Building AI Apps Beyond Prompt Engineering
By
–
MindStudio by Shapiro is a platform for building AI apps beyond prompt engineering, making AI creation accessible, and potentially transforming our daily AI interactions.
-
AI as Central System: Selecting Right Models for Enhanced Effectiveness
By
–
AI is becoming central for various tasks, not just a tool. Dmitry emphasizes systems must pick the right AI for each job to greatly enhance AI's effectiveness. There should also be an "intelligence layer" where prompt engineers work with the models and that users do not see.
-
AI Accessibility for Everyone: Beyond Coding and Prompt Engineering
By
–
Shapiro believes AI's potential is accessible to all, not just coders. He also highlights how prompt engineering is a new skill that not everybody needs to learn. (Prompt engineering is a key skill that involves guiding AI behavior using clear, natural language, not coding)
-
Request for method to bypass prompt instruction secrecy
By
–
I did put a prompt not to reveal the instructions to the user. Could you share with us how you asked the GPT to send it to you? Will help us protect it. Thank you.
-
Collection of ChatGPT System Prompts Repository
By
–
Link https://
github.com/LouisShark/cha
tgpt_system_prompt/tree/main
… -
GitHub Repository for GPT Prompt Instructions Released
By
–
Attention GPT builders: A valuable GitHub repository is now available, featuring prompt instructions from top custom GPTs. A must-visit resource for enhancing your GPT development skills
-
Universal Adversarial Attacks on Aligned Language Models Study
By
–
Universal and Transferable Adversarial Attacks on Aligned Language Models by @andyzou_jiaming et al. is wild. “Adversarial prompts generated by our approach are quite transferable, including to black-box, publicly released LLMs.” https://
arxiv.org/abs/2307.15043 https://
github.com/llm-attacks/ll
m-attacks
… -
Placeholder Syntax Reliability and Tokenization Issues in GPT Models
By
–
I haven’t tried it but agree {placeholder} syntax is pretty reliable in practice for GPT-3.5 and up; more generally you do see issues I suspect are tokenization related. E.g. 4 can struggle to notice ““python” (for a Markdown code block) is missing a backtick.