latest experiment: a social media scheduler that runs locally on my computer, no need for subscriptions or going through hops to connect the social media APIs. You login manually, write and schedule a post and the application will try to upload in all the social media accounts connected.
It can use local models for error correction and to try to recover if something fails while posting.
Background removal used to need an external service or model and nowadays you can do it almost instantly and local on a Mac. Works well for most image types too!
Asking Claude Code to make an html page to explain different things has become one of my favourite things to do when trying to understand something.
diagrams, images, graphs and everything in a single file.
People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.
We share our approach, early results, and a quick look at our model in action.
https://t.co/AFJZ5kH7Ku
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
2/n - like geoguessr but with sounds from around the world. The game has now over 300 sounds, working on making the hint more interesting
https://t.co/CXz59XhOu0
Silly idea of the day: I realised I don’t mind Youtube ads if they're in a language I don’t understand. So I made a browser extension to replace the ad audio with random funny sounds. 3/5 works great!
Starting to make my apps have revokable api keys so they can be used directly with agent systems like OpenClaw. Makes for a nice symbiosis, app and UI for the human and rest, text based with any agent and even UI on demand
@hjcg1988@openclaw For my pi 4 I installed ubuntu server on it, installed the openclaw cli(curl -fsSL https://t.co/MROxcORXVy | bash) and just proceeded with the wizard for local configuration
@hjcg1988@openclaw I'm using OpenAI's codex-5.2( for the agent), whisper(for audio messages processing), text-embedding-3-small(for memory embeddings).
Starting to play with different models for the like grok 4.1 fast as well.
Cost is just the apis usage, depends of subscription or api key