Shortsmark
Extract actionable insights from short-form videos
What it does
That video you bookmarked? You were never going to rewatch it. And if you had, you’d have just opened the app and started scrolling again. Shortsmark skips the rewatch and hands you the idea directly—so the time you’d have spent scrolling is time you get back. Shortsmark extracts, structures, and saves actionable insights, technical takeaways, and mental models from short-form video platforms into a distraction-free workspace designed for action rather than continuous consumption.
Instant capture, full-context recall, and an external memory built to think like you. Save any public link and Shortsmark keeps the idea, with a citation back to where it came from.
Shortsmark turns long videos, articles, and documents into a personalized feed of posts you can read in seconds. Built for the modern mind: fast enough to scroll, structured enough to study, and grounded enough to trust. They already understand your industry’s problems — unlike direct competitors, they’re incentivized to help you. Urgency is worth more to the buyer than a discount is worth to you — find out how fast they need it first. Leading with the limit you designed around stops the room from re-litigating it after you finish. Understand difficult material one point at a time, with every TL;DR linked back to its complete source thread. Start by naming the constraint. Confirm the…from shortsmark.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 · 10d 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