✍️ Prompt Engineering - zhuangda · Scour

Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience 🤖AI

Prompts are technical debt too 🤖AI

seangoedecke.com·23h·Lobsters, Hacker News

Prompt Engineering for Agentic AI 🤖AI

machinelearningmastery.com·1d

brendanddev/explaind: Cognitive steering layer for Gemma 4, structured prompt physics for shaping reasoning trajectories without fine-tuning. 🤖AI

github.com·1h·DEV

Stop Fixing Your Prompts — Fix Your Thinking Style Instead (A Claude Code Experiment) 🤖AI

bestaiweb.ai·1d·DEV

I Built an AI Tool That Turns Bad Prompts Into Expert-Level AI Responses 🤖AI

promptcraft-genai.netlify.app·17h·DEV

Four-Tier Memory Hierarchy for LLM Reasoning (USC, UW) ✅evals

semiengineering.com·5h

What I Observed While Using AI Prompts in Real Work 🤖AI

·5d

AI Coding Tools Need Better Boundaries, Not Better Prompts 🤖AI

youtu.be·2d·DEV

Learnings from 100K lines of Rust with AI (2025) 🤖AI

news.ycombinator.com·8h·Hacker News

Playing With AI 🤖AI

evantravers.com·21h

Does Your Project Need an LLM, Machine Learning or Statistics? ✅evals

builtin.com·4h

5 AI Prompts That Get You Production-Ready Code Every Time (Copy-Paste Ready) 🤖AI

musfique3.gumroad.com·2d·DEV

How to A/B Test LLM Prompts Without Breaking Production ✅evals

benchwright.polsia.app·5d·DEV

Why Your AI Agent Is Inconsistent (It’s Not the Prompt) 🤖AI

asianefficiency.com·6h

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-⁠Play 🤖AI

vmax.ai·2h·Hacker News

Prompt Engineering Is Just Debugging a Black Box 🤖AI

siliconopera.com·1d

When your AI assistant has the keys to production 🤖AI

helpnetsecurity.com·18h

MoE expert co-activations: Reordering inputs yields easy throughput gains. 🤖AI

blog.doubleword.ai·41m·Hacker News

Evals before prompts: building an LLM OCR for KYC ✅evals

blog.nilenso.com·2d

Log in to enable infinite scrolling