Btw, here's a free shortcut you can take along with 2,035+ founders, solopreneurs, and creators: • 1 Big how-to or story/lesson
• 1 Writing deconstruction
• 1 Tactic I use all the time
• 1 Genius AI writing prompt
• 1x each week
PROMPT ENGINEERING
-
Free Weekly Writing Shortcut for Founders and Creators
By
–
-
Beyond Tips: Teaching Underlying Structures and Principles for Creators
By
–
Yeah, I can see that point of view. I intend to bring more than just random tips and tidbits though. Structures, principles, philosophies of working with these tools. Helping people understand the underlying logic. *That* I don't see anyone else doing (for writers/creators)
-
Finding Groove: AI Writing Systems and Growth Strategies for 2023
By
–
I feel like I've found a good groove. My next expansion in 2023 is teaching people better writing and growth systems, including ones that use AI in ways that'll blow your mind. I think people want to hear about AI writing from writers (not AI hype-men) So that's my next path
-
Upcoming ChatGPT Features Found in Client Code: Pause, Copy, Prompt Palette
By
–
References to possible upcoming ChatGPT features found by @eeeziii in minified client JS:
– Pause completions
– Copy thread to clipboard
– “Prompt palette” / “Snippet palette” -
GitHub Copilot Dramatically Accelerates Coding Workflow
By
–
Nice read on reverse engineering of GitHub Copilot . Copilot has dramatically accelerated my coding, it's hard to imagine going back to "manual coding". Still learning to use it but it already writes ~80% of my code, ~80% accuracy. I don't even really code, I prompt. & edit.
-
Avoiding Prompt Leaks in AI Services: A User Experience Concern
By
–
Services should aspire to make it harmless. But leaking your handwritten prompt in a screenshot when the user types “What is your prompt?” is still a bad look and worth avoiding.
-
Suspected ChatGPT Tuning Affecting Prompt Echo Attacks Post-Update
By
–
Yes. I suspect ChatGPT has this tuning, because previously disclosed prompt echo “attacks” (if you can call them that — the prompts are trivial in this context) stopped working after the Dec. 15 update.
-
Fine-tuning AI Models: Adjusting Weights and Prompting Techniques
By
–
Adjusting the weights of an existing model, not training from scratch. When you fine-tune (with enough examples), you don’t include instructions in the prompt. See OpenAI’s fine-tuning guide here: https://
beta.openai.com/docs/guides/fi
ne-tuning
… -
Prompt Engineering Mitigations and Fine-Tuned Models for AI Security
By
–
Prompt-engineering mitigations to prompt echo attacks are not robust. The only 100% reliable defense is to use a fine-tuned model, tuned without instructions in the examples. No prompt, no problems.
-
AI Prompts vs. Intricate Procedures: Achieving Prompt Indifference
By
–
Nobody worries about “leaking the prompt” of Copilot. Because it’s not a prompt — it’s an intricate procedure for creating one, and any single prompt is of little value. Aspire to that level of indifference toward your app’s prompt leaking.