Tagged "prompt-engineering"
- Sol-5.6 and Opus 5 Models Demonstrate Strong One-Shot Game Performance
- Claude Code Cut System Prompt by 80%: Implications for Small Local Models
- ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline
- GLM-5.2's Code Reviews Are Only as Good as Your Prompt
- Good LLM Development and Usage Patterns
- Three Flavors of Coding with AI Agents
- How I Used a Local LLM to Organize the Store on My NAS
- I Think I Figured Out What an AI IDE Looks Like
- LLM Hallucinations in the Wild
- Improving Code Quality with Local Claude and Codex Models
- Self-Hosted LLMs in Production: Real-World Limits and Practical Lessons
- Using a Local LLM as a Zero-Shot Classifier
- 16 Ways to Make a Small Language Model Think Bigger
- Claude vs Local LLM: Real-World Prompt Comparison Reveals Trade-offs
- Gemma 4 Template Improvements Enhance Tool Use and Dialog Compliance
- Reverse-Engineering the Apollo 11 Code with AI
- Show HN: Open Agent Spec – Treat AI Agents Like Typed Functions, Not Prompt Chains
- Qwen 3.5 Models: Optimal Settings and Reduced Overthinking Configuration
- Self-Hosted AI Code Review with Local LLMs: Secure Automation Guide
- You're Using Your Local LLM Wrong If You're Prompting It Like a Cloud LLM
- Practical Fix for Qwen 3.5 Overthinking in llama.cpp
- Show HN: TLDR – Free Chrome Extension for AI-Powered Article Summarization
- Qwen 3.5-27B Demonstrates Exceptional Performance with Thoughtful Prompt Engineering
- Every agent framework has the same bug – prompt decay. Here's a fix
- TemplateFlow – Build AI Workflows, Not Prompts
- Why AI Models Fail at Iterative Reasoning and What Could Fix It
- Ask HN: How Do You Debug Multi-Step AI Workflows When the Output Is Wrong?