✍️ Prompt Engineering - zhuangda · Scour

DeepClause “Turbo DML” Agent Harness 🤖AI

deepclause.substack.com·12h·Substack

I Cut My LLM API Bill by 38% With a Caching Layer — Here's the Complete Implementation 🤖AI

xidaoapi.com·2d·DEV

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

blog.nilenso.com·3d

How I Survived 7 Rebuilds of the Same SaaS by Building a Control Layer Around Claude Code 🦆DuckDB

raxsoft.gumroad.com·21h·DEV

LLM Observability with Self-Hosted Langfuse and vLLM 🤖AI

pyimagesearch.com·2d

The Oldest LLM Trick Still Works in 2026 — I Found It on Two Production AI Apps 🤖AI

infosecwriteups.com

·6d

Cloudflare Agents docs 🗃️SQLite

developers.cloudflare.com·12h

AI Paper Review: Language Models are Few-Shot Learners (GPT-3) 🤖AI

freecodecamp.org·2d

The Importance of Being Idempotent 🤖AI

campedersen.com·14h·Hacker News

Agentically optimizing LLM prompt cache TTLs for fun and profit 🗃️SQLite

blog.firetiger.com·2d·Hacker News

☕🤖 Tutorial: Launch a Word-of-Mouth Referral Engine in 60 Minutes 🤖AI

theaibreak.substack.com

Breaking the Black Box: A Case Study in Red-Teaming a Government Education AI 🤖AI

sentinelone.com·2d

Prompt Optimization for LLM Code Generation via Reinforcement Learning 🤖AI

Why does off-model SFT degrade capabilities? 🤖AI

lesswrong.com·2h

Prompting Amazon Nova 2 for content moderation 🔄HTMX

aws.amazon.com·2d

aditya-r123/iMessage-Bot: AI that automatically crafts and sends replies to your contacts and group chats 🤖AI

github.com·3h·Hacker News

The problem of induction (heads), pt. II 🤖AI

seantrott.substack.com·12h·Substack

AI Security Evaluation: How to Test Prompt Injection, Data Leakage, and Unsafe Tool Calls 🤖AI

·1w

Agent Development Lifecycle (ADLC) 🤖AI

dsebastien.net·2d

How I Decompose Any Image Into Recomposable Layers on Melius 🤖AI

scopeful.org·19h·DEV

Log in to enable infinite scrolling