biwills's comments

On: iTerm2 critical security release

[biwills]

Kitty (https://sw.kovidgoyal.net/kitty) has been my go to for many years and with tmux it's fantastic.

I have heard a lot of great things about https://ghostty.org/ but haven't had a chance to check it out

edit: oops, I misread your question as "what alternatives are there"

[clwg → biwills]

My only issue with kitty and tmux is that I always have to copy over my terminfo files manually or else I get a 'xterm-kitty': unknown terminal type error.

[ISO-morphism → clwg]

I've done the same, but in case you didn't know Kitty can do that automatically (though it does a bit more that you may or may not want it to do)

https://sw.kovidgoyal.net/kitty/kittens/ssh/

[ilrwbwrkhv → biwills]

Kitty is really the only superior editor beyond ghostty terminal iterm weztwrm alacritty foot and others and the only one worth recommending.

[alt187 → ilrwbwrkhv]

No it's not. The author smuggles opt-out telemetry and is suspiciously abrasive towards users pointing this out.

https://github.com/kovidgoyal/kitty/pull/3544

[ComputerGuru → alt187]

No, he’s not. Calling this telemetry is a stretch and that’s his style on everything he disagrees with (unfortunately).

On: Text Editing Hates You Too (2019)

[biwills]

I'd say it's less about covering all edge cases and more about showing that text editors are insanely complex, and it doesn't take long to find edge cases that text editors with 10s/100s of millions of users have.

On: Text Editing Hates You Too (2019)

[biwills]

This reminds me of Marijn Haverbeke's, the author of CodeMirror and Prosemirror, blog post about making the first version of CodeMirror

https://codemirror.net/1/story.html

On: NPM package is-even has over 140k weekly downloads

[biwills]

From the description of the repo on GitHub:

> I created this in 2014, the year I learned how to program. All of the downloads are from an old version of https://github.com/micromatch/micromatch.

On: Faraday.dev – Connect your phone to LLMs running o...

[biwills]

Yes, but we have more details on our cloud offering coming soon

On: Faraday.dev – Connect your phone to LLMs running o...

[biwills]

Hey HN,

Excited to share Mobile Tethering, our latest feature release on Faraday.dev. It lets you run local LLMs on your Mac/Windows Computer (Linux soon) and seamlessly use them to chat with AI on mobile. Since all the heavy workloads run directly on your computer (instead of on an expensive cloud server), it's 100% free to use, and your chat data is never stored or logged in the cloud.

I'm one of the founders of Faraday.dev, so would love to hear any ideas you have on what we should build next!

__

PS: For those who've never used Faraday – it's a zero-config desktop app for creating AI characters (custom chatbots) powered by locally running LLMs. Faraday can run on CPU with only 8GB of RAM via llama.cpp by @ggerganov, and the app will automatically use your GPU to speed things up. We also have a community-driven Character Hub, text-to-speech, lorebooks, and more.

On: Many options for running Mistral models in your te...

[biwills]

Yes. Here's a quick rundown of grammar in llama.cpp (link on the docs of faraday.dev which runs llama.cpp under the hood)

https://docs.faraday.dev/character-creation/grammars

On: Code Llama, a state-of-the-art large language mode...

[biwills]

We are doing this with https://Faraday.dev - would love to chat more - my email is on my profile!

On: LLM Constellation

[biwills]

we've been looking at at a lot of custom models for https://faraday.dev (shameless plug)

There's already some interesting fine tuned llama2 models:

- https://huggingface.co/NousResearch/Redmond-Puffin-13B - https://huggingface.co/Tap-M/Luna-AI-Llama2-Uncensored

[LoganDark → biwills]

i don't like redmond-puffin because it makes the mistake of baking "human" into the training data, which is quite difficult to avoid as it's a pretty common practice... and unfortunately it looks like luna-ai-llama2-uncensored bakes "assistant" into the training data!

so both those models are probably not suitable for simulating interactions between non-human, non-AI entities... the chronos and hermes models only do input/instruction which are incredibly generic and you can just eschew the format altogether, and it follows chats correctly with no bias towards human/user/assistant.

that app looks very interesting though, reminds me of something that we were planning to make, but gave up because winui xaml is too cursed