AI Loop Engineering: Separating Hype from Practice
Bob Reynolds6 days ago
Prompt Engineering
17 stories tagged Prompt Engineering.
AI. Bob Reynolds6 days ago
AI Loop Engineering: Separating Hype from Practice
Loop engineering is the latest term developers are chasing. A new video argues the fundamentals — prompt, context, harness — still matter more than the label.
When Small AI Models Beat Frontier Ones on Your Tasks
Dev Kapoor3 weeks ago
AI. Dev Kapoor3 weeks ago
When Small AI Models Beat Frontier Ones on Your Tasks
RL Nabors walks through a real eval framework for replacing frontier model calls with local SLMs—and the results are more nuanced than the pitch suggests.
Claude Skills: The AI Filmmaking Workflow Upgrade
Marcus Chen-Ramirez2 months ago
AI. Marcus Chen-Ramirez2 months ago
Claude Skills: The AI Filmmaking Workflow Upgrade
CyberJungle's Claude Skill approach reframes AI video prompting as specialized craft—separate tools for character sheets, storyboards, and Seedance 2.0 shots.
Stop Prompting. Start Questioning Your AI Agent
Rachel "Rach" Kovacs2 months ago
AI. Rachel "Rach" Kovacs2 months ago
Stop Prompting. Start Questioning Your AI Agent
AI strategy creator Nate B Jones says prompt engineering is dead. His 'AI Question Method' has real merit—but there's a data privacy conversation he's skipping entirely.
The Hidden Layer Wasting Your AI Workflow Time
Marcus Chen-Ramirez2 months ago
AI. Marcus Chen-Ramirez2 months ago
The Hidden Layer Wasting Your AI Workflow Time
Prompts, skills, plugins, MCPs—most AI users conflate them all. Here's what each one actually does and why the distinction matters for real work.
AI Skills at Scale: Teaching Agents Your Standards
Rachel "Rach" Kovacs2 months ago
AI. Rachel "Rach" Kovacs2 months ago
AI Skills at Scale: Teaching Agents Your Standards
Nick Nisi and Zack Proser of WorkOS make the case that structured markdown 'skills' are how you stop re-explaining yourself to AI agents every single day.
Cursor Replaced 15,000 Lines of Code with 200 Lines of Markdown
Marcus Chen-Ramirez3 months ago
AI. Marcus Chen-Ramirez3 months ago
Cursor Replaced 15,000 Lines of Code with 200 Lines of Markdown
How Cursor's David Gomes deleted a complex feature and rebuilt it with prompts—plus the very real problems that came with trusting models instead of code.
The Caveman Skill Makes AI Shut Up and Save You Money
Zara Chen3 months ago
AI. Zara Chen3 months ago
The Caveman Skill Makes AI Shut Up and Save You Money
New Claude skill cuts AI verbosity by 45%, potentially saving token costs—but the math gets complicated. Here's what actually works and what doesn't.
Power Users Are Breaking OpenClaw in Interesting Ways
Marcus Chen-Ramirez4 months ago
AI. Marcus Chen-Ramirez4 months ago
Power Users Are Breaking OpenClaw in Interesting Ways
Matthew Berman spent 200 hours optimizing OpenClaw. His setup reveals how AI agents work when you push past the defaults—and what breaks along the way.
AI That Improves Itself: Autoresearch Meets Claude Code
Marcus Chen-Ramirez4 months ago
AI. Marcus Chen-Ramirez4 months ago
AI That Improves Itself: Autoresearch Meets Claude Code
Andrej Karpathy's autoresearch framework now optimizes AI prompts autonomously. Developer Nick Saraev demonstrates how it works—and what it costs.
Why Most People Are Using Claude Code Wrong
Bob Reynolds4 months ago
AI. Bob Reynolds4 months ago
Why Most People Are Using Claude Code Wrong
AI coding assistants work best when you stop treating them like tools and start treating them like collaborators. Here's what actually matters.
ASCII Art Planning Could Fix AI Coding's Biggest Problem
Samira Barnes5 months ago
AI. Samira Barnes5 months ago
ASCII Art Planning Could Fix AI Coding's Biggest Problem
Developer Mark Kashef demonstrates how ASCII wireframes before coding with Claude could reduce iterations, save tokens, and prevent 'vibe coding' disasters.
Claude's Agent Teams Are Doing Way More Than Code Now
Zara Chen5 months ago
AI. Zara Chen5 months ago
Claude's Agent Teams Are Doing Way More Than Code Now
AI developer Mark Kashef shows how Claude Code's agent teams handle business tasks—from RFP responses to competitive analysis—that have nothing to do with coding.
Your Claude.md File Is Sabotaging Your AI Code
Yuki Okonkwo5 months ago
AI. Yuki Okonkwo5 months ago
Your Claude.md File Is Sabotaging Your AI Code
That config file you haven't touched in months? It's creating cascading errors across your entire codebase. Here's why less is actually more.
Decoding Vibe Coding: The New AI Frontier
Bob Reynolds6 months ago
AI. Bob Reynolds6 months ago
Decoding Vibe Coding: The New AI Frontier
Explore vibe coding: AI-assisted development with potential pitfalls and transformative possibilities.
Demystifying Claude Code: Simple Models, Big Impact
Tyler Nakamura7 months ago
AI. Tyler Nakamura7 months ago
Demystifying Claude Code: Simple Models, Big Impact
Explore how Claude Code simplifies AI coding agents with simple models and better prompt engineering.
Enhancing GLM-4.7: Transforming an Open Model into a Coding Powerhouse
Dev Kapoor7 months ago
AI. Dev Kapoor7 months ago
Enhancing GLM-4.7: Transforming an Open Model into a Coding Powerhouse
Boost GLM-4.7's coding prowess with strategic prompts for backend logic and frontend design.