LLM Chat via SSH • Hacker News Board

Re: LLM Chat via SSH

#21

Post by xigoi » Mon, Jun 16, 2025, 9:31 PM UTC

It’s not clear from the README what providers it uses and why it needs your GitHub username.

Re: LLM Chat via SSH

#22

Post by halJordan » Tue, Jun 17, 2025, 2:53 AM UTC

amelius wrote: post #5

I'd rather apt-get install something. But that seems not a possibility in the modern days of software distribution, especially with GPU-dependent stuff like LLMs. So yeah, I get why this exists.

What is the complaint here? There are plenty of binaries you can invoke through your cli that will query a remote llm api

Re: LLM Chat via SSH

#23

Post by ccbikai » Wed, Jun 18, 2025, 1:45 AM UTC

xigoi wrote: post #21

It’s not clear from the README what providers it uses and why it needs your GitHub username.

Connects to any OpenAI-compatible API.

Using a GitHub username prevents abuse.

Re: LLM Chat via SSH

#24

Post by ccbikai » Wed, Jun 18, 2025, 1:47 AM UTC

demosthanos wrote: post #14

Skimming the source code I got really confused to see TSX files. I'd never seen Ink (React for CLIs) before, and I like it! Previously discussions of Ink: July 2017 (129 points, 42 comments): https://news.ycombinator.com/item?id=14831961 May 2023 (588 points, 178 comments): https://news.ycombinator.com/item?id=35863837 Nov 2024 (164 points, 106 comments): https://news.ycombinator.com/item?id=42016639

Many CLI applications are now using Ink to write their UIs.

I suspect React will eventually standardize all UI writing approaches.

Re: LLM Chat via SSH

#25

Post by ccbikai » Wed, Jun 18, 2025, 1:48 AM UTC

gclawes wrote: post #12

Is this doing local inference? If so, what inference engine is it using?

Currently using the OpenAI API to access multiple models. You can use ollama to access local inference models