VVrushika D·Oct 29Prompt Injection Through QR-Linked Content: Testing the Security of AI-Powered ApplicationsQR codes have made it easier than ever to access websites, documents and online services. A quick scan can take users to almost any kind of digital content. But what happens when an AI application rea7 min read·digitalqr.hashnode.dev1
PPowerduck·Oct 25After three hours the agent defended the wrong model it invented, because the session remembered the assumption better than the factsLong chat history anchors on the first plausible model the agent invents, and late corrections read as exceptions instead of a rewrite. The session keeps defending the early guess. Keep a verified-facts brief at the top and re-derive from source files rather than trusting session memory.4 min read·blogs.powerduck.com
Cccprompt·Sep 29The AI Art Prompt Formula: 7 Layers That Make Your Images Look ProfessionalStop generic AI art. Master the 7-layer prompt formula — subject, style, lighting, composition, color, texture — with 10 examples.16 min read·ccprompt.hashnode.dev
SShraddha bhat·Sep 26CO-STAR: A Deep Dive Into the Prompt Framework That Fixes Vague AI OutputsA practical breakdown of Context, Objective, Style, Tone, Audience, and Response — with worked examples, common mistakes, and how it compares to RISEN and CRAFT10 min read·aiinsights1909.hashnode.dev1
Aaiglelevant·Sep 14So, What Even Is RAG?RAG sounds complicated as hell. It’s not. Here’s how LLMs find the right info, use it, and stop making shit up.5 min read·aiglelevant.hashnode.dev
SSunney Sood·Sep 11How Large Language Models Actually Work: From Your Prompt to Every Word They WriteA complete, plain-English mental model — from tokens to attention to the exact moment ChatGPT picks its next word. When you type a question into ChatGPT and an answer appears a few seconds later, it26 min read·sunneysood.hashnode.dev
CChristian Johannsen·Sep 10Permissions vs. Policies in LLM Systems: What Matters WherePermissions set what an LLM agent can do. Policies decide what it should do. Why system prompts aren't security controls, and where each belongs.7 min read·breakglass.hashnode.dev
SSundarapandy·Sep 4Prompt Engineering: Designing Effective LLM PromptsLearn effective LLM prompt engineering with practical techniques for context, constraints, examples, output formats, security, and reliable AI systems2 min read·ai-tech-insights.hashnode.dev18A
PPRANAV THAWAIT·Jul 23Compile Once, Run Anywhere: Supporting Multiple LLM ProvidersPromptForge: Type-Safe Prompt Engineering with TypeScript4 min read·omnikon.hashnode.dev
PPRANAV THAWAIT·Jul 21Prompt Composition: Reusing Prompts Like ComponentsPromptForge: Type-Safe Prompt Engineering with TypeScript4 min read·omnikon.hashnode.dev
