Pro tip: take any github repo url, change the “g” to a “u” (like “uithub”) and you’ll have a copyable, LLM-optimized prompt that contains a structured version of the repo!
PROMPT ENGINEERING
-
AI Model Fails at Sestina Poetry Generation Task
By
–
Flops on the sestina in a very weird way. It seems absolutely unable to hit the end word scheme that many smaller models succeed at (albeit without the s constraint). Have tried it a few times in different ways. Curious.
-
Scale, Tool Use, and Multimodal: AI Development Path Forward
By
–
It looks like scale + tool use + multimodal remains the chosen path forward.
-
Vibe Coding vs Thoughtful Coding with AI: Key Differences
By
–
*in my mind, vibe coders are just yolo’ing code with AI – which i think of distinctly from “coding with AI” which is more thoughtful
-
Veo 3 Video Generation: Fast Results with Simple Prompts
By
–
Most of these were on the faster, cheaper Veo 3, using a dumb prompt, and worked the first time. For Ophelia, I just used the famous painting itself and the prompt: she sits up and says "Actually, I think I am over Hamlet"
-
Community Creates Amazing Videos with Veo 3 Fast
By
–
Our community is already making wild stuff with Veo 3 Fast.
— Replicate (@replicate) 9 juillet 2025
Here are some of the best creations — with prompts you can try yourself.
🧵👇
1. https://t.co/42lY4hwD6l pic.twitter.com/aypHXJrJOVOur community is already making wild stuff with Veo 3 Fast. Here are some of the best creations — with prompts you can try yourself. 1. http://
replicate.com/p/y1qq2n6209rm
a0cqy2rvf5ddjg
… -
Which AI Model and Advanced Features Did You Use?
By
–
What model did you use? Did you turn on Thinking? Did you use Plan/Act?
-
Using Browser Validation with Cline for Code Review
By
–
Bonus: if you’re using @cline and there’s frontend you can use to validate, add to the end of the prompt: “In addition to reviewing the code, use the browser as well to review your changes.”
-
Improve Coding Agents with Verification Prompts
By
–
Here's a trick that helps improve results when working with coding agents: After the system finishes writing code, ask: "I want you to go through each change you made and cross-check it against my prompts. Did you do everything perfectly? Have you made any mistakes?"
