251–260 of 1001 posts
I have a couple of other apps that I have plans for, as well. If I get sick of playing traffic cop, with the phone app, I may take a break, and work on them.
Keep working on a test automation library that should allow writing browser/mobile tests easier with LLMs help, so I could focus more on testing, and less on automating.
Planning a hobby alpaca farm (3-4 alpacas), very early stage. Everything from farm related stuff (water, food, shelter, etc.) to self-sufficiency (solar, etc.) to real time monitoring (which cameras, affecting power supply). Who knows if it'll ever happen, but just planning everything in detail is a lot of fun. Especially with weird regulatory constraints where I'm living, there's a lot to watch out for. Example: Sol…
https://github.com/damien/content-security-policy/tree/main/...
Once I’m happy with my take on a reference implementation I’m hoping to create some tooling with it to do some interesting analysis of CSP abstract syntax trees to identify things like policy anti patterns, reporting on capabilities a policy grants to a domain/resource, and a better mechanism for allowing tools like OPA, SemGrep, etc. to define and enforce rules on a policy.
In the app you pick a folder with videos in it and it stores the path, metadata, extracts frames as images, uses a local whisper model to transcribe the audio into subtitles, then sends a selection of the snapshots and the subtitles to an LLM to be summarised. The LLM sends back an XML document with a bunch of details about the video, including a title, detailed summary and information on objects, text, people, animals, locations, distinct moments etc. Some of these are also timestamped and most have relationships (i.e this object belongs to this location, this text was on this object etc). I store all that in a local SQLLite database and then do another LLM call with this summary asking for categories and tags, then store them in the DB against each video. The App UI is essentially tags you can click to narrow down returned videos.
I plan on adding a natural language search (Maybe RAG -- need to look into the latest best way), have half added Projects so I can group videos after finding the ones I want, and have a bunch of other ideas for this too. I've been programming this with some early help from Aider and Claude Sonnet. It's getting a bit complex now, so I do the majority of code changes, though the AI has done a fair bit. It's been heaps of fun, and I'm using it now in "production" (haha - on my PC)
I've been working on an e-ink laptop. I wanted a machine I could stare hours at and feel okay about it. I didn't seem to find a device like that out there. I'm designing everything from the chassis to the software OS. E-ink has its own design constraints. I'm building 5 apps for it: a browser, reader, mail, writer and code editor. It's still a ways to go. Here's a picture of what I have so far: https://www.heyravitej…
Here's a couple related videos: