NSNavayuvan Subramanianinblogs.navayuvan.com·12h ago · 5 min readHow I Built a Fully Async Feature Pipeline With Claude, Notion & VercelSix months ago, I could only write code when I was sitting at my desk, laptop open, fully present. That's just how it worked. You need to develop a feature, you sit down and build it. That was the dea00
AGAkshit Gandotrainakshitg.hashnode.dev·15m ago · 5 min readThe Anatomy of an LLM Vulnerability: Analyzing the OWASP Top 10 for GenAIThis blog is a part of the #DataAndAI Series When we deploy traditional web applications, we know how to define boundary lines. We validate input formats, we sanitize database queries, and we construc00
CCookCodePratikinaiengineering123.hashnode.dev·13h ago · 20 min readBest Self-Hosted AI Coding Tools in 2026: A Practical Guide for Enterprise Development Teams"Which AI model writes the best code?" Instead, engineering leaders are asking a different set of questions. Can our source code remain inside our infrastructure? Can the AI understand our entire r11B
AKAlex Kerninalexkern.hashnode.dev·23h ago · 13 min readThe loop threw away my memory system, optimizing cache hits on llm modelsI set out to solve a cost problem. A long Claude session gets more expensive the more it grows. With Opus, a session sitting around 100k tokens runs me roughly a few dollars; at 200k it's about $10; a00
VJVivek J. Patilinvivekpatil23.hashnode.dev·15h ago · 7 min readHybrid Retrieval with RRF: How I Got 100% Retrieval Precision in ContextQuery The Problem With Naive RAG Nobody Talks About Most RAG tutorials show you the same pipeline: embed your documents, store vectors, embed the query, fetch the top-k nearest neighbors, pass to LLM. It wo00
SRSukalyan Royinsukalyanroy.hashnode.dev·16h ago · 16 min readDoes Your System Prompt Actually Do Anything? I Built an Eval to Find OutI maintain a single global system prompt that every AI coding agent I use reads. One file, shared across Claude Code, Antigravity and OpenAI's Codex. I tune it constantly: tighten a rule here, cut a p00
STShantanu Tomarinshantanutomar.hashnode.dev·3h ago · 17 min readBuilding a Fair Workload-Aware Ticket Assignment System with a Local LLMEvery engineering team has work that does not look expensive on paper but quietly drains a lot of attention. For me, that work was ticket triage. I work with a small engineering team of five developer00
MDMatthew Davisinsaasapp.hashnode.dev·4h ago · 2 min readWhy You Should Be Checking Your SaaS Visibility in LLMs, Not Just GoogleTo grow your SaaS visibility you should be checking your LLM visibility across many different queries, and doing what's needed to improve it regularly. For this I'd recommend using a proper AI Visibil00
VVasilisindaimones.hashnode.dev·7h ago · 11 min readDPO vs RLHF: The Alignment Tax You Pay Without KnowingEvery aligned model pays the alignment tax. RLHF and DPO both trade reasoning capability for corporate agreeableness. Here is what that costs you — and why honest AI requires a different approach. As00
VVasilisindaimones.hashnode.dev·8h ago · 13 min readOpenAI vs Open Source: An Aristotelian Defense of Intellectual FreedomOpenAI started as a nonprofit for intellectual freedom. It became the most valuable closed-source AI company on Earth. Aristotle predicted exactly this. OpenAI was founded as a nonprofit with a missi00
