Walmart's bestselling $20 weekender bag is 'so pretty' and great for spring travel
It comes in a whopping 21 colors.
pokitdog.com
The Best Concealed Carry Guns of 2026, Tested and Reviewed
There are lots of great carry guns on the market. We've tested most of them over the past few years. Here are our top picks.
Zirco.ai – AI employee for dental front desk operations
Hi HN,I'm building Zirco.ai — an AI administrative employee for dental practices.The problem: dental front desks spend 2–3 hours every day manually verifying insurance benefits through carrier portals. On top of that, they're handling inbound scheduling calls, sending reminders, coordinating referrals, and managing new patient intake — all manually, all repetitive, all expensive. A single front desk employee costs $40–50K/year and turns over at 40% annually.What I built: an AI tha
Sharp on Sight | Sharpening Services | Sun Prairie
Restoring a sharp edge often brings tools back to life in a way that surprises people.Sharp scissors are safer, more efficient, and far more enjoyable to use. If your scissors are struggling to cut the way they once did, proper sharpening can make a dramatic difference.Sharp on Sight | Sharpening Services | Sun Prairie
Launch HN: Relari (YC W24) – Identify the root cause of problems in LLM apps
Hi HN, we are the founders of Relari, the company behind continuous-eval (https://github.com/relari-ai/continuous-eval), an evaluation framework that lets you test your GenAI systems at the component level, pinpointing issues where they originate.We experienced the need for this when we were building a copilot for bankers. Our RAG pipeline blew up in complexity as we added components: a query classifier (to triage user intent), multiple retrievers (to grab information from di
“The Right Path to Choose:” Blackfolium on Innovation, Design, and the European Future of the Tactical Equipment
In the current body armor industry, innovation and practical design are becoming increasingly sought after, driven by rising geopolitical tensions and evolving ballistic threats. Among many companies tackling the industry’s […]
The Reaper just won’t quit: Try as they might, the military can’t ditch the MQ-9
It’s not stealthy, it’s getting up there in years and it doesn’t have the payload of fifth-generation fighter jets. Despite that, the MQ-9 Reaper drone system isn’t going to the bone yard.In fact, the Reaper is a reliable and frequently used weapon in the U.S. military’s arsenal, popping up among forward-deployed forces in conflict zones around the world. Most recently, the Pentagon revealed it was one of several airframes taking part in the war in Iran, or Operation Epic Fury,
Budget BOB backpack weight test part 2 review
Budget B.O.B. backpack weight test showing load limits and capacity.
Show HN: Core Rth. A governed AI kernel for engineers who don't trust their LLMs
Hey HN,I spent the last 20 years building enterprise software and cybersecurity tools. Last year I started using AI agents for real work — and got terrified. Every tool I tried would happily `rm -rf /` if you phrased it right. One popular agent literally tried to exfiltrate SSH keys (you might have seen that HN post).So I built Core Rth. It's not a chatbot wrapper. It's a Sovereign Cognitive Kernel — an AI backend where every LLM action is a proposal that must survive a governance
AI Is a Lethal Threat This Year
My name is Joel Gross and I am a Washington state resident who founded a tech company in 2009 that now has over 250 full-time employees.Improvements in artificial intelligence have reached the takeoff point and are increasing exponentially. AI has already exceeded human intelligence by most measures. This year, we will see it far exceed human capabilities. The problem is that we are basically birthing a new form of life, one that will not care about human wants or needs. Most people who have stu
Show HN: I built proxy that keeps RAG working while hiding PII
Hey HN,When you send real documents or customer data to LLMs, you face a painful tradeoff:- Send raw text → privacy disaster - Redact with [REDACTED] → embeddings break, RAG retrieval fails, multi-turn chats become useless, and the model often refuses to answer questions about the redacted entities.The practical solution is consistent pseudonymization: the same real entity always maps to the same token (e.g. “Tata Motors” → ORG_7 everywhere). This preserves semantic meaning for vector search a
Show HN: Context-compact – Summarize agent context instead of truncating it
agents. Not a custom truncation strategy, not a sliding window, not dropping old messages and hoping for the best. The failure mode is well-understood: your context window fills up, you truncate from the top, and the agent loses the thread. It forgets the task it was working on, the file path it just wrote to, the UUID it needs to reference. The conversation breaks. The problem is everyone keeps solving it by throwing away information instead. Truncation is fast to implement and quietly wrong. T
Show HN: Dorkly – automated Google dorking that somehow survives captchas
Hi HN, I built Dorkly, an app (mobile and desktop) for discovering public documents across the web. It’s basically automated Google dorking. Instead of manually running queries like: filetype:pdf machine learning site:edu cybersecurity pdf intitle:"research paper" filetype:pdf Dorkly generates and explores them automatically and returns a feed of PDFs, DOCs, PPTs, manuals and research papers. The fun part: it does this at scale and still manages to avoid the usual capt
Show HN: OpenClaw-superpowers – Self-modifying skill library for OpenClaw agents
I built a skill library for OpenClaw (always-on AI agent runtime, not session-based) where the agent can teach itself new behaviors during normal conversation.The idea: you tell your agent "every time I ask for a code review, always check for security issues first." It invokes a create-skill skill, writes a new SKILL.md, and that behavior is live immediately — no restart, no config change, no developer required.What I think is actually useful (the safety cluster):• loop-circuit-brea
VA announces plan to put some veterans in guardianships
The Trump administration is launching a new plan to initiate legal guardianship proceedings for hundreds of the “most vulnerable” veterans in the country. The administration announced the move on Wednesday, saying that the Department of Justice and Department of Veterans Affairs agreed to a plan that would see VA attorneys appointed as special assistant U.S. attorneys, allowing them to start and participate in state court conservatorship and guardianship proceedings, according t
EDC Knives Are on Sale Starting at Just $10 for Prime Day
We may earn revenue from the products available on this page and participate in affiliate programs. Learn more ...
8 Tactical Flashlights That Turn Night Into Day
From a pocket-size EDC light to a 7,000-lumen powerhouse, these rugged flashlights are built for emergencies, vehicles, camping, and everyday carry.
Show HN: Chrome extension that tailors your resume to a job posting in one click
Job tailoring advice is everywhere but it all bottlenecks at the same place: actually doing it 50 times. Copy resume, paste into ChatGPT, rewrite bullets, reformat everything that broke, repeat. Ajusta sits on the job page (LinkedIn, Indeed, etc.), reads the posting, and rewrites your resume against the JD without touching your formatting or adding anything that isn't already there. The output is your resume with tighter language and better keyword alignment, not a new document built from a
Show HN: Excalidraw Architect MCP for AI Based IDEs
Hey Folks, I've been building an MCP server that generates beautiful Excalidraw architecture diagrams fully auto-laid-out, no manual positioning. It's open source, works with any AI IDE (Cursor, Windsurf, etc.).I wanted to share it early because the core layout engine is solid and already producing clean diagrams.What Problem Am I Solving? AI IDEs generate architecture diagrams as Mermaid or ASCII art. When they attempt Excalidraw, they hallucinate coordinates and boxes overlap, arrows
Show HN: Porchsongs.ai; Rewrite chordcharts/lyrics with AI to make them personal
I posted porchsongs here about a month ago as a self-hosted Docker project. A few people looked at it, but I get that spinning up docker containers and configuring stuff is sort of a big ask.So I went ahead and built it into an actual hosted platform. Core is still fully usable and OSS but now I offer a hosted option.I'M OPENING IT UP VIA AN INVITE CODE. Here's one for the first 100 HN users so my LLM token budget doesn't immediately go to zero haha:PORCH-7F95BBtl;dr backstory. I