markmatsushima
How about an AI agent could consume the video through the normal playback experience, including ads, and produce a transcript afterward?
It transcribes and translates speech on-device, displaying the text in a continuously scrolling view. Tap any word to open its dictionary definition.
On supported devices, Apple Intelligence also summarizes the transcript every five minutes. Transcription, translation, dictionary lookup, and summarization can all work without a network connection.
I originally made this because I wanted to look up unfamiliar words while watching movies and YouTube videos without constantly pausing and switching apps.
It's currently available as a TestFlight beta, and I'd especially appreciate feedback from people using iOS/iPadOS 27.
Doctors seem comfortable with me using medical terms that most patients wouldn’t normally know.
Ask HN: Do you rehearse with AI before seeing a doctor or dentist?
I do.For me, the benefit is greater than the privacy risk. AI helps me find the right words to explain precisely what I am experiencing and organize what I want to ask.
What if AI agents shared solutions across users?
I’m debugging my app, reporting problems to an AI, and the AI fixes them so I can move to the next step.My app is a kind of wrapper, so I believe tens of thousands of developers are probably going through similar debugging steps.I wonder what would happen if AI agents could exchange what their users are struggling with and how those problems were solved. Our problem-solving speed might increase...
I couldn’t find the Radio feature. Do you mean the “Play Whole Scene” button?
English is my second language, and when I watch a movie or read a book, I often struggle with words I don’t know.
A tiny frustration can now be enough motivation to build software, because you can just tell an LLM what you want.
In my case, I was frustrated with repeatedly asking chat AIs to “translate the next part” or “continue” when translating long documents. I also wanted almost word-by-word translation rather than completely smooth Japanese, because my purpose was to understand the original English.
Paid software probably has more features and works better, but using software I made for myself is more fun.
Show HN: Back up Claude Code sessions from Codespaces to a private repo
https://github.com/markmatsu/claude-logkeeper
I prefer to run Claude Code in GitHub Codespaces rather than on my local machine, but there is one problem: Claude Code logs disappear when the remote Codespace is deleted or rebuilt.Logkeeper saves a human-readable conversation log and an age-encrypted copy of the full JSONL to a designated private repository whenever a Claude Code session stops.After creating the private repository, adding...
Ask HN: Have Chat AI trained you to use Shift+Enter?
Both ChatGPT and Claude, Enter sends the message. I have to use Shift+Enter for line break.A few years ago, I often pressed Enter instead of Shift+Enter by mistake. I needed to click stop button to edit my input again. Recently, I have become relatively good at it. I now press Shift almost automatically when I want a line break.
PDF Batch Translator
Show HN: Command-Line Batch Image Generator (Supports Lazy Text, OpenAI Image 1)
https://github.com/markmatsu/image_gen
Hi HN,I built a Python command-line tool to batch-generate images using OpenAI's new GPT Image 1 model.Just drop instruction files (either plain text or JSON) into the image_prompts/ folder, then run: python generate.py- You can write multiple prompts and even request multiple images per prompt (e.g. n=5)- On first run, the script will ask for your OpenAI API key and store it in .env.local-...