The killer app for ChatGPT is writing that no one reads. E.g., research papers.
PROMPT ENGINEERING
-
Avoiding Multiple Heads in Stable Diffusion Higher Resolution
By
–
Any tips how to avoid multiple heads at higher res in Stable Diffusion?
-
LLM Tokenization Trick for EOT Emission
By
–
It’s not willing to produce what it thinks is an EOT token. You have to trick it by making it emit a sequence of tokens that re-tokenize to the EOT token after being turned into a string.
-
Weekly Newsletter: How-to, Writing Deconstruction, Tactics, AI Prompts
By
–
Get my weekly fresh perspective enjoyed by 2,035+ founders, solopreneurs, and creators. Audience-building + monetization:
• 1 Big how-to or story/lesson
• 1 Writing deconstruction
• 1 Tactic I use all the time
• 1 Genius AI writing prompt -
Creating Advanced GPT Prompts Beyond Basic Expectations
By
–
There are some decent websites and repos, but imo, the prompts are too basic and they teach you to lower your expectations. I've been creating a GPT prompt toolkit that's higher level. Could easily be expanded to bible level. What info and references would you want to see?
-
Perplexity AI enables filtered tweet searches with SQL queries
By
–
This is doable with @perplexity_ai already. See for example:
"top tweets of @amasad that are not about replit" https://
perplexity.ai/sql?uuid=5ffc8
201-713d-4d32-9bdf-49a673eeb473
… -
ChatGPT Impresses with Code Understanding but Makes Logic Error
By
–
That thread is what made me go attempt to do some of my work today with ChatGPT — optimizing a chunk of logic was on my todo list, so I asked ChatGPT. I was really impressed by how it understood the code, but then it made the logic error.
-
ChatGPT vs. Claude: Comparing AI Models with a Literary Prompt
By
–
Side-by-side comparison: @OpenAI
's ChatGPT vs. @AnthropicAI
's Claude Each model is asked to compare itself to the machine from Stanisław Lem's "The Cyberiad" (1965) that can create any object whose name begins with "n": -
Chains Generate Long Original Content: Screenplay Example
By
–
a great example of this is https://
arxiv.org/abs/2209.14958 – it uses chains to create long and original generations (whole screenplays) -
Data Augmentation and Chaining for Enhanced AI Responses
By
–
+1, data augmented generation will be key for insightful responses also chaining can help generate a more complex response in multiple steps