anonfunction
Joined 13 years ago
Karma
2,245
Submissions
938
Member since
Mar 15
Recent submissions
Comment · 2 months ago
I've been looking for a markdown editor that let's me print the rendered view and have yet to find one. Which is quite surprising given how many there are. I just use my own webapp for now, should probably open source it in case anyone else is looking for this functionality.
If you know of a nice mac app that let's me easily write / view and print markdown I'd love to hear from you!
Comment · 3 months ago
There's this: https://platform.kimi.ai/docs/guide/kimi-k3-quickstart
Comment · 4 months ago
This is something I've been working on exposing to AI labs through my startup LatentEvals[1], and found similar results in other industries from lending to insurance claims.
Happy to share some sample reports if anyone is interested!
Comment · 4 months ago
There are multiple "sandbox backends"[1] available besides Vercel currently. I'm sure more will follow, and it's open-source so you could always implement your own.
Comment · 4 months ago
One of the preeminent Zig software projects, Tigerbeetle[1], has a great website[2] and markdown file[3] for what they call TigerStyle.
It's honestly a great read as a human but also I packaged it as a skill and saw coding agent improvement, especially around memory usage.
3. https://github.com/tigerbeetle/tigerbeetle/blob/main/docs/TI...
Comment · 4 months ago
Love these types of projects, really useful and helpful. Sharing with my daughter!
Comment · 5 months ago
I'm the creator of hty, as part of my work for building custom eval suites at LatentEvals.com I found that AI agents struggled with interactive CLI / TUIs and would resort to setting flags that may be outdated or not exist at all.
I needed a way for AI agents to use all the software that humans do, things like htop, k9s, create-next-app, and even nethack.
How it works: hty wraps any interactive cli in a persistent PTY session. Your agent "sees" the rendered terminal the way you do and types the way you would. I've had a lot of success with agents being able to get through interactive npx setups, play terminal games, and create logical commits from a bunch of work in an long claude code session by using git add -p for interactively patching the git stage.
It's available to use as a simple skill so it works for almost all agents, but you can also use it as the human via the CLI. It's written in zig and built on top of libghostty.
https://github.com/montanaflynn