Hidini
AI & Notes ovelay, hidden on screen sharing
What it does
A lightweight AI overlay for Mac that screen sharing can't see. Hit a hotkey to screenshot anything on your screen and get the answer back. Feed it your CV and a job posting and the answers match your background, not a textbook. Ask follow-ups in the chat layer. Set sticky notes only you can read. Transcribe an audio call as it happens. Zoom, Meet and Teams can't see any of it. Hidini also supports BYOK and local AI. Fast, built with Native Swift, under 4 MB. Free to try, no subscription!
Real-time transcription, AI hints, and screen analysis in an overlay invisible to Zoom, Meet, and Teams. Native macOS app, no subscription.
Hidini helps you pass any live call or technical interview. It solves the task on your screen, answers the question you were just asked, and surfaces it all in a subtle, undetectable way. One invisible overlay holds four tools: live transcription, AI hints, screen analysis, and full keyboard control. Every hint is built from your CV and the job posting, so what lands on screen fits your background and what the role is screening for. Hit one hotkey to grab the entire screen, or another to draw a selection around just the part you care about. The AI analyzes the captured image, understands the full situation, finds the problem, and returns a complete solution. No typing or speaking required.…from hidini.com
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 9d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 16d ago · simedw.com