I totally agree with you. I guess, for me, it's more about the extent of the things they can do. Like, people may not be aware that they can "talk" to a PDF, replicate image styles, or run code natively, etc.
To this day, I still get surprised by the things it can do, so it's
PROMPT ENGINEERING
-
Surprising AI Capabilities: PDFs, Images, Code Execution
By
–
-
5 ChatGPT hacks for easier learning and memorization
By
–
98% think ChatGPT can be used to skip learning. But no one mentions that ChatGPT makes learning easier. Here are 5 ChatGPT hacks to memorize everything:
-
GPT-4 Text Handling and Information Hiding Techniques
By
–
Part of the magic is that GPT-4 can read text written this way but in any other context you would need a decoder on the other side. And if you allow a decoder there are lots of ways to hide information in non-printing chars like ZWSP etc.
-
AI Image Generation: Unexpected Fairy Elements in Hair
By
–
Yeah, and when I prompted for fairies it just went and put them in her hair.
-
Adding Conversational Memory to RAG Applications
By
–
Adding conversational memory to your RAG app The main UX for LLM applications is chat. That makes it important to know how to add conversational memory to your apps – including you RAG apps! @curious_kaylynn walks through how to do exactly that!
-
Local LLM RAG Demo with Creative User Experience Design
By
–
The demo below is really interesting for a few reasons:
— LangChain (@LangChain) 14 janvier 2024
🦜Uses local LLMs (seems like @MistralAI via @ollama)
🌲RAG integration for PDFs and web pages
Even more exciting to us though… it changes up the UX! It's not just simply a chat text box
Super creative and practical https://t.co/PLGOO01NO8The demo below is really interesting for a few reasons: Uses local LLMs (seems like @MistralAI via @ollama
)
RAG integration for PDFs and web pages Even more exciting to us though… it changes up the UX! It's not just simply a chat text box Super creative and practical -
Leveraging Conversational AI for Enhanced Critical Thinking
By
–
4. The Power of Conversation Interaction with language models like ChatGPT facilitates exploration. The back-and-forth dialogue enhances output by encouraging critical thinking. Ken views the "hallucinations" as beneficial since they force deeper questioning.
-
ChatGPT as Pair Programmer: Validation Over Blind Acceptance
By
–
2. ChatGPT as a Pair Programmer Ken views ChatGPT like a pair programmer – it forces him to think more and validate the code rather than blindly. accept it. The "hallucinations" make him engage more.
-
Optimizing LLM Interaction: Starting Fresh vs. Long Thread Tuning
By
–
It often feels like starting a new chat and re prompting from scratch is much faster than trying to tune the long thread where smth went wrong before
-
Use capital letters for words you want in generated output
By
–
Prompt Tip #3: Writing the word that you want it to generate using capital letters. For example:
Use “The name ‘SKYLINE TECH’ integrated into a logo with a futuristic city skyline, with the name ‘SKYLINE TECH’ integrated” instead of “The name ‘Skyline Tech’ integrated into a