Why rip off Apple design so much here (see homescreen image). Seems like a lot of unnecessary effort. Plus it’s not done well enough so instead of looking like itself, it looks like a bad ripoff.

Thanks for your awesome work. Never thought I’d switch to a terminal without cmd-f, but ghostty made it worth it. Can’t wait for v1.3!

Shell over MCP, with multiple options for sandbox. Includes Docker, Podman, Modal, E2B, and WASM:

https://github.com/Kiln-AI/Kilntainers

Can run anything from a busybox in WASM to a full cloud VM. Agent just sees a shell.

This seems to be billed as a MCP server for making sandbox containers... right? Doesn't this kind of miss the whole point?

"Make me a sandbox for yourself! Make sure its really secure!"

The sandboxing options are set when you connect the MCP to the agent, not by the agent passing params about its own sandbox.

There’s a misconception about the right security boundary for agents. The agent code needs secrets (API keys, prompts, code) and the network (docs, other use cases). Wrapping the whole agent in a container puts secrets, network access, and arbitrary agent cli execution into the same host OS.

If you sandbox just the agent’s CLI access, then it’s can’t access its own API keys/code/host-OS/etc.

I’m also getting “saw you on GitHub” spam from voice.ai

And they are using a different domain for the emails so the spam markers don’t hit their primary domain.

Agreed.

Join me in double-dash em proximates. Shows you manually typed it out with total disregard token count and technical correctness.

Just yesterday I saw Claude.ai use double dashes in its responses for the first time...

Exactly... How long until people figure out that LLMs emulate common writing patterns as their sole reason for being

Yes. To be fair, I was always a barbarian who just typed a hyphen in-place of an emdash and figured that was good enough. The only REAL em-dashes in my pre-AI writing are the result of autocorrect.

How is this running the vm/container? Cloud or something like container2wasm?

Kinda cool I’m on my phone, on an alpine terminal, and genuinely need to ask if it’s running in the browser.

checked from desktop: WASM container!

This looks amazing. I’ve been wanting virtualization.framework micro VMs for months! Docker is fine, but the overhead isn’t ideal.

I like the defaults (ephemeral, network off). Any thoughts on adding host-mapped directories?

I have a MCP server for ephemeral sandboxes that supports various backends (Docker, E2B, Modal, even WASM). I’ll look at adding this. https://github.com/Kiln-AI/Kilntainers

It’s llama 3.1 8B. No vision, not smart. It’s just a technical demo.

why is everyone seemingly incapable of understanding this? waht is going on here? Its like ai doomers consistently have the foresight of a rat. yeah no shit it sucks its running llama 3 8b, but theyre completely incapable of extrapolation.

note: they jumped from 18 to 26 to align to the year.

I can't believe Apple hasn't pushed an update to their 9-year-old device in 11 years!

Earlier today I asked ChatGPT if my car keys had and proximity sensing features I could use to find them (ends up they were in the couch).

It said yes! Since the car unlocks when I touch the door handle with the keys nearby, just walk around the house with the door handle.