Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Language models on the command line

simonwillison.net

Post reply on HN
Print view View original

41–46 of 46 posts

Re: Language models on the command line

#41

Post by josephrmartinez »

simonw wrote: post #5

This was a workshop I gave in my https://llm.datasette.io/ CLI tool. What other CLI tools are people using to work with LLMs in the terminal? There one comment here about https://github.com/paul-gauthier/aider and Ollama is probably the most widely used CLI tool at the moment: https://github.com/ollama/ollama/blob/main/README.md#quickst...

A CLI tool for generating tutorials based on the work you recently committed: https://github.com/josephrmartinez/mktute

npm i mktute

You can select between local model (ollama), claude 3.5 sonnet, or gpt-4. I've been surprised to find sonnet much better in performance and price for this task.

Re: Language models on the command line

#42

Post by iJohnDoe »

dvt wrote: post #13

Fantastic work here! I'm working on a local tool, affectionately called Descartes, which does something similar—but with a spotlight-like UX for the non-hackers out there. I do think that LLMs have the potential to fundamentally change the way we interact with our computers. There's a lot of edge cases (especially when combining it with the inaccurate science of screen readers) but it's pretty mind-blowing when it wo…

Really cool! Do you plan to release it?

Re: Language models on the command line

#43

Post by ziml77 »

jgalt212 wrote: post #36

Every time I see an LLM demo, I'm blown away. Every time I use one for myself, I feel like a fool. I say this because the scraper demo bit looks very neat, but I've been down this path before and I don't want to waste my time getting bad or deceptively incorrect results.

When you're looking at a demo, the results just have to look good enough for the demo to be impressive. When you're actually using it, the results actually need to be good.

Re: Language models on the command line

#44

Post by fragmede »

simonw wrote: post #5

This was a workshop I gave in my https://llm.datasette.io/ CLI tool. What other CLI tools are people using to work with LLMs in the terminal? There one comment here about https://github.com/paul-gauthier/aider and Ollama is probably the most widely used CLI tool at the moment: https://github.com/ollama/ollama/blob/main/README.md#quickst...

Open interpreter.

Open Interpreter lets LLMs run code on your computer to complete tasks. Eg "fix my python" or "make a movie out of the pictures in this directory."

https://github.com/OpenInterpreter/open-interpreter

Re: Language models on the command line

#45

Post by mikeqq2024 »

throwup238 wrote: post #8
simonw wrote: post #5

This was a workshop I gave in my https://llm.datasette.io/ CLI tool. What other CLI tools are people using to work with LLMs in the terminal? There one comment here about https://github.com/paul-gauthier/aider and Ollama is probably the most widely used CLI tool at the moment: https://github.com/ollama/ollama/blob/main/README.md#quickst...

> What other CLI tools are people using to work with LLMs in the terminal? I use aichat: https://github.com/sigoden/aichat I especially like the terminal integration where I can type a natural language request at the terminal and press Alt+E to have it converted to a command to run.

There is similar ShellOracle: https://github.com/djcopley/ShellOracle

It is used as Bash widget, where you press CTL-F, describe your command, then press Enter, the generated command will be inserted into your shell prompt.

Re: Language models on the command line

#46

Post by nbbaier »

mark_l_watson wrote: post #37
simonw wrote: post #5

This was a workshop I gave in my https://llm.datasette.io/ CLI tool. What other CLI tools are people using to work with LLMs in the terminal? There one comment here about https://github.com/paul-gauthier/aider and Ollama is probably the most widely used CLI tool at the moment: https://github.com/ollama/ollama/blob/main/README.md#quickst...

My workspace for experimenting with LLMs is chaotic: currently about a 100 Python scripts that each have a single purpose. I sometimes use Ollama or Golamma from the command line. Since I am an old Lisp hacker, I also have a large collection of short Racket and Common Lisp LLM experiments. Chaos.

You should use an LLM to classify and consolidate them lol
Post reply on HN