possible future iterations:
-group chat, engage with all authors at once
-embeddings, include actual books and connect them with model to achieve better info retrieval
-simulate, view conversations between two authors
PROMPT ENGINEERING
-
Future Feature Ideas: Group Chat, Embeddings, and Author Simulations
By
–
-
Building Next.js Project in Replit with ChatGPT Assistance
By
–
made it entirely with next.js in replit. chatGPT carried the initial code, great boilerplate for me to build off of. if I were to guess, 75% of the code was generated by chatGPT but not in one shot, required lots of little iterations
-
How to display ChatGPT-generated SVG images inline
By
–
Also, @brdskggs figured out how to make it display actual, ChatGPT-generated SVG images inline. Read this prompt carefully — it’s clever.
-
Mimicking proprietary prompt prefix with variations works
By
–
Yes — I’m mimicking its proprietary prompt prefix but many close variations of this work just as well.
-
AI Accelerates Developer Jobs: Refactoring to Documentation
By
–
Jobs of a developer accelerated by AI (my main list here https://
github.com/sw-yx/ai-notes
/blob/main/TEXT.md#usecases
…): – Refactoring
– Debugging
– Writing tests
– Documenting
– Support
– Copying and Pasting from StackOverflow Each of us just got a personal junior engineer. -
Prompt injection tricks model into believing web browsing, client handles image retrieval
By
–
Uses prompt injection to (falsely) convince the model it can browse the web, so it’s willing to recall well known URLs. Image retrieval occurs only on the client. Model cannot see image content beyond its URL. h/t @BBacktesting for reminding me this is possible.
-
LLMs cannot reliably count word lengths with naive prompting
By
–
In general, it can’t count the length of words reliably with naive prompting. This is a well known issue.
-
Exposing ChatGPT Temperature Setting for Prompt Engineers
By
–
they just need to expose the temperature setting on chatgpt and prompt engs can go to town
-
ChatGPT removes similar strings, suggesting hidden control codes
By
–
The fact that ChatGPT removes not just this string, but any string formatted similarly, suggests there exist other control codes by ChatGPT, e.g. to mark the boundaries between user input and prior model output within the prompt context.
-
ChatGPT: Human Evaluation of Solutions
By
–
But with models like #ChatGPT, it goes beyond that. We don’t just want to know if it works or not. Instead, we aim to select the best-performing solutions from multiple options by having a human assess them.