Add in human-written techniques Ask ChatGPT it to work according to good advice you've read elsewhere. In the prompt below, I take some tips on persuasive writing from the Grammarly blog and ask it to apply them to my topic.
LLMS
-
Simulate an Expert: ChatGPT Role-Playing Techniques
By
–
Simulate an expert Ask ChatGPT to play the part of a customer, co-host, or talented expert. Have a conversation with it, or ask it to generate content as if it were that specific persona.
-
10 Advanced ChatGPT Techniques to Master AI Prompts
By
–
Everyone’s using ChatGPT. But almost everyone's STUCK in beginner mode. 10 techniques to get massively ahead with AI: (cut-and-paste these prompts)
-
LangChain Improves Agent Max Iterations Handling with Final LLM Pass
By
–
More graceful handling of agent max iterations Previously, when an agent reached max iterations, it just stopped with a fixed message Now it makes one final forward pass through the LLM to generate a best guess final answer h/t @johnjnay for idea https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/max_iterations.html
… -
OpenAI Staff Discuss AI Model Tuning and Unforeseen Improvements
By
–
OpenAI staff have told me that they didn’t specifically tune on these questions and I believe them. The improvements are seen even for newly made-up problems in the same style.
-
ChatGPT Reformats Code: Request, Error Stack, Solution
By
–
More things count as formats than you are used to. The conversational nature of ChatGPT allows you to feed in more info, blending human and machine to work together better than either could alone. Here we see a reformat of Initial request + Error stack trace => Working Code https://
x.com/RReverser/stat
/RReverser/status/1599184983402446848
… -
ChatGPT Reformatting: Quick Wins with Minimal Knowledge Requirements
By
–
“ChatGPT reformatting” requires minimal world knowledge, are instantly verifiable, and can reliably save minutes of work multiple times a day. The reformat can include contextual inference, which saves even more time at the cost of a bit more risk:
-
ChatGPT’s True Killer App: Information Reformatting
By
–
ChatGPT’s current killer app isn’t search, therapy, doing math, controlling browsers, emulating a virtual machine, or any of that other cherrypicked examples that come with huge disclaimers. It’s a lot more quotidian: Reformatting information from any format X to any format Y.
-
Will Generative AI Replace Developer Jobs? Impact Analysis
By
–
Will AI replace developer jobs? Amazing twitter space by @ykdojo on how generative AI like GPT-3, ChatGPT will change the landscape for developer jobs.
-
Prompt Injection Discovery and Attribution: A History Correction
By
–
A history correction: I am not the first to discover prompt injection. I was merely the first to do so and discuss it publicly. PI was discovered independently by multiple teams. The first was Preamble, an LLM security company, whose find predates mine by several months.