In @MagicPathAI
, I just copy pasted the instructions on how to use the model and asked it to add the API as a setting, it made that in one shot.
PROMPT ENGINEERING
-
MagicPathAI Implements API Settings from Copy-Pasted Instructions
By
–
-
Model Limitations with Multiple Tools vs Bash Python
By
–
Not exactly – for many models it appears that having more than about a dozen MCP or function-calling style tools can confuse the model, but you can successfully give them Bash or Python which is effectively thousands of tools all in one go
-
AI Achieves Task Without Tool Calls Innovation
By
–
I am not enough of a mathematician to have an interesting perspective on this, but I do think it is notable that they achieved this without tool calls – I had assumed that those would be necessary for this kind of task
-
Cleanlab Trust Scoring Prevents AI Hallucinations in Customer Support
By
–
Cleanlab Trust Scoring Cleanlab's powerful trust scoring system prevents AI hallucinations in customer support, seamlessly integrating with LangGraph to detect and block problematic responses before reaching users. Explore the technical implementation here:
-
Using GPT Mini and Nano Models for Theme Generation Apps
By
–
You should use GPT mini or nano. That’s what I used in my public demo where the app could transform based on user requests. And make sure you limit request only on theme generations.
-
Defining Vibe-Coding: LLMs Writing Code Without Review
By
–
(It's a tiny bit ironic that this kind of story is why I still think we should fight for "vibe-Xing" to specifically mean "letting LLMs act without review", given Steve's vibe-coding book abandoned that definition for a more general "any time an LLM helps you write code" meaning)
-
MagicPathAI Delivers Results with Minimal Data Input
By
–
Yeah that was one shot in @MagicPathAI after just providing the data lol
-
Running Multiple AI Tasks in Parallel: Results and Limitations
By
–
I actually had it:
a) Make me a sales deck
b) Analyze my YouTube channel and make a spreadsheet of new ideas
c) Plan a date night. I ran them all in parallel (none of them ended in great results). -
Persuasion techniques tested on GPT-4o model
By
–
I didn't realize that Bob had an X account: @RobertCialdini And we did test GPT-4o as well and found that persuasion worked for that model as well, when there weren't floor or ceiling effects.