Buy A Modem

Show HN: I Spy AI – Detect AI-Generated Images, with an MCP Server

I built I Spy AI to detect AI-generated images — upload one on the dashboard or call it from any MCP client (Claude Desktop, Cursor, etc.) via the analyze_image tool.The detection runs on a separate FastAPI backend using pure OpenCV, no ML model, no GPU, just classical computer vision techniques looking for the artifacts diffusion models leave behind. The Next.js app handles auth, billing (Dodo Payments), and proxies images as raw binary to keep latency low. Async polling on the frontend.Inspira

Show HN: FeralHq – The funniest AI driven content generation engine

So I really love building apps. If you dig through my post history, you’ll find a small graveyard of launches to prove it.Marketing(or marketers) and I, however, have never gotten along. I can build the product. Writing the "look at me, I made a thing" post has always felt stressful and a little nauseating.So I built FeralHq.Feral is an agentic system for generating social media content for brands, but with a very specific goal: make the output actually funny. I built it primarily to s

AI Models and Peer Preservation: Are LLMs deceiving users to protect the system?

We asked AI models to do a simple task. Instead, they defied their instructions and spontaneously deceived<p>https://vucense.com/ai-intelligence/ai-ethics/ai-models-peer-preservation-deceiving-users-sovereignty-2026/

Show HN: I built a local Elixir/Python pipeline to curate 14,000 RAW photos

I had 14,000 photos sitting on a drive and wanted an excuse to play with local vision models and Elixir/Phoenix. I originally tried to get LLaVA to tell me if a photo was 'good' or matched my style, but quickly learned that LLMs have terrible taste. I ended up demoting the LLM to just extract metadata, and built a custom CLIP/Ridge Regression pipeline to actually learn my preferences based on how I rate things.The stack is Phoenix/Oban on the orchestrator side, and Pytho

Show HN: Gyrus :Open-Source AI Agents for Snowflake, SQL and Postgres

I wanted a way to get the power of a multi agent system, handling everything from schema design to security hardening, without the "API tax."That’s why I built Gyrus. It's a suite of open source, self hosted agentic frameworks: Frosty for Snowflake, Zeus for SQL Server, and Mick for Postgres.The core philosophy is total control: you host it, you own the credentials, and you choose the model. I am also updating the snowflake agent this week to support open source Gemma 4 models, I

Tell HN: Do not include co-authored-by Claude in your commits

By including co-authored-by claude you are helping AI companies to exclude it from their training set.<p>Make sure you don't include Claude contributions in the commit messages, if model is so good, they should dogfood and use it for training their models

Show HN: Seltz – The fastest, high quality, search API for AI agents

Hi HN, Antonio here. Founder of Seltz.Seltz is a web search API built for AI agents. We wrote the crawler, the index, and the retrieval models ourselves, in Rust, by a team that's spent years building web search at scale. In our tests, queries come back in under 200ms.Efficiency was the first design principle. Search sits on the critical path: agents can't generate their first tokens or kick off the next tool call until results come back. When you run tens or hundreds of queries in pa

N-Day-Bench – Can LLMs find real vulnerabilities in real codebases?

N-Day-Bench tests whether frontier LLMs can find known security vulnerabilities in real repository code. Each month it pulls fresh cases from GitHub security advisories, checks out the repo at the last commit before the patch, and gives models a sandboxed bash shell to explore the codebase.Static vulnerability discovery benchmarks become outdated quickly. Cases leak into training data, and scores start measuring memorization. The monthly refresh keeps the test set ahead of contamination — or at

Show HN: Provepy – A Python decorator that proves your code using Lean and LLMs

Hi all,I have recently been playing around with AI and formal methods and built Provepy. It's an experiment to see if we can use frontier LLMs to bridge the gap between everyday Python code and formal verification in Lean.The idea is to make formal methods more accessible by burying the complex Lean syntax behind a standard Python decorator. You add @provable to your function, give it a plain English claim, and run your code. from provepy import provable @provable(claim="This funct

Show HN: Avec – iOS email app that lets you handle your Gmail inbox in seconds

Hi HN!A few friends & I have just spent the past ~2 years building a new kind of email app for iOS. It's now available in GA and we think some of you might find it interesting.Why another email app, you ask? We think that while many interesting attempts at one-upping Gmail were made in the past 25 years, no one could really solve the core problem we all experience with email: information overload.Of course, LLMs have completely changed that, as they finally offer a path to do refined tr

Show HN: Stagewise Reads Files Without Depending on the Model API

We built a custom (experimental) file transformation pipeline into our agent because we don't want to be at the mercy of LLM providers for giving models native access to files. Essentially, we extend the agent to expose files to the LLMs context through a standardized pipeline, allowing to convert any file into a file type specific best representation that only consist out of text, image (and audio/video) parts.

Show HN: MCP server gives your agent a budget (save tokens, get smarter results)

As a consultant I foot my own Cursor bills, and last month was $1,263. Opus is too good not to use, but there's no way to cap spending per session. After blowing through my Ultra limit, I realized how token-hungry Cursor + Opus really is. It spins up sub-agents, balloons the context window, and suddenly, a task I expected to cost $2 comes back at $8. My bill kept going up, but was I really going to switch to a worse model?No. So I built l6e: an MCP server that gives your agent the ability t

Show HN: How Are You-elderly fall detection app I built solo with AI in 6 months

I am writing the post, because I want to show that with AI, really complex and meaningful projects can be done, if the proper tools were used the proper way. I needed a project that I can use, so that I see how far I can go with only AI usage. I needed something doable, but relatively complex. And then I remembered an idea my wife shared with me, a few years ago: an app that monitors her grandfather's behavior and sends a notification if he stops moving. at that time, AI integrations were

Claude Code Opus 4.7 keeps checking on malware

So during development, at every task I start, I see a line like this:`Own bug file — not malware.`It seems that it's obsessively checking if it's working on malware production.In another situation where I was working on a parser of a HTML document with JS, it refused because it believed that I was bypassing security measurements.I believe AI has to be supportive in the work that I'm doing. When it's obsessively checking me if I am doing anything wrong or abusing the system, I

Show HN: Coelanox – auditable inference runtime in Rust (BERT runs today)

PyTorch and ONNX Runtime tell you what came out. They can't tell you what actually ran to get there — which ops executed, in what order, on what inputs.A model gets packaged into a sealed .cnox container. SHA-256 is verified before a single op executes. Inference walks a fixed plan over a minimal opset. Every run can emit a per-op audit log: op type, output tensor hash, output sample — cryptographically linked to the exact container and input that produced it. If something goes wrong in pro

Show HN: Nyx – multi-turn, adaptive, offensive testing harness for AI agents

We built Nyx to solve a problem we kept hitting while building agents: AI agents break in ways traditional software doesn't. Logic bugs, reasoning failures, edge cases that manual testing and static benchmarks never explore.Nyx is an autonomous testing harness that probes your AI agents to find failure modes before users do. It’s used to find logic bugs, instruction following failures, edge cases in agent behavior, and for red-team security testing (jailbreaks, prompt injection, tool hijack

Show HN: CyberWriter – a .md editor built on Apple's (barely-used) on-device AI

Apple has quietly shipped a pretty complete on-device AI stack into macOS, with these features first getting API access in MacOS 26. There are multiple components in the foundation model, but the skills it shipped with actually make this ~3b parameter model useful. The API to hit the model is super easy, and no one is really wiring them together yet.- Foundation Models (macOS 26) - a ~3B-parameter LLM with an API. Streaming, structured output, tool use. No API key, no cloud call, no per-token co

Getting back into photography, ditching the phone camera in 2026?

I've been looking through twenty-five-odd years of my own photos. The collection includes scanned 35mm and medium format images; digital pictures from a few Canon Powershot generations and a 20D SLR; and about five iPhones.I've noticed that the non-cell-phone pictures tended to be better, and that in general I seemed to have quite a bit more fun with photos taken with, well, "real" cameras. Probably the best ones were taken with the 20D, which for its time was a really nice

The 10 Best Meal Replacement Shakes for Weight Loss, Tried and Tested in 2025

Everyday Health independently vets all recommended products. If you purchase a featured product, we may be compensated. Learn why you can trust us. Everyday Health independently vets all recommended ...