What Was I Watching
Remember every show. Share the good ones.
What it does
Remember what you were watching. Share the good ones. Add shows by camera OCR, Siri, or manually — then share rich cards with friends who can add them in one tap. iPhone, Apple Watch, widgets, Spotlight, iCloud sync. Free. Built in 17 days with spec-driven AI development — 3 days of decisions before a single line of code. Full story on Medium.
Does the same job
all alternatives →
- W2Watchlater 2.0 for iPhone and iPad2011 · ▲19
Watchlater, a sleek service for bookmarking, downloading and sharing videos. You can now have all your favorite videos at one place, and watch them anytime and anywhere with both our iPhone and iPad App. Get the app from the App Store: http://goo.gl/HkiSv Or visit our new revamped website: http://watchlaterapp.com/ If you don't know what to bookmark then try our most popular bookmarks: http://watchlaterapp.com/popular If you have feedback, we're eager to hear it here in the comments ;-)
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 · 17d 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 · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
