Ask HN: What Are You Working On? (July 2026)
91–100 of 1001 posts
Re: Ask HN: What Are You Working On? (July 2026)
#92Re: Ask HN: What Are You Working On? (July 2026)
#93Re: Ask HN: What Are You Working On? (July 2026)
#94Re: Ask HN: What Are You Working On? (July 2026)
#95i make the microsoft word but less sucks, and there is scientific calculator integrated and also ai on it too, available on linux (stable) and windous (unstable).
Re: Ask HN: What Are You Working On? (July 2026)
#96I continue to grow my main product BoltAI[1]
[0]: https://inka.page
[1]: https://boltai.com
Re: Ask HN: What Are You Working On? (July 2026)
#97I went on a side quest to strip out ProseMirror and markdown-it and implement a custom stack instead. I open sourced both the parser and editor (https://saturn9.studio/technology/):
* Markoffset is a fast, plugin-based, incremental Markdown parser: https://github.com/saturn9studio/markoffset
* Scribeframe is a text editor engine: https://github.com/saturn9studio/scribeframe
Re: Ask HN: What Are You Working On? (July 2026)
#98Re: Ask HN: What Are You Working On? (July 2026)
#99It's connected to all papers of course, and all kinds of scientific simulators and specialised models. But I'm currently in Shanghai talking to labs to join a CloudLab (and hopefully setting up our own robotic labs), so that AI can actually order real physical experiments that are executed cheaply, efficiently and seamlessly as tool calls.
Through experiments like autoresearch we have seen that AI is already, if not always smarter, at least more systematic than humans at following the scientific method relentlessly (hypothesis-experiment loop). Let's see what we can do by connecting it to the real-world :)
Re: Ask HN: What Are You Working On? (July 2026)
#100It is build using a model that can classify messages (ham/spam/marketing), packaged for Apple Mail but could be used in other places.