Live data from Hacker News

Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

github.com

51–60 of 73 posts

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#51

We've gone full circle: efficient meta languages back to inefficient and ambivalent natural language.

I'm endlessly amused by the fact that among the first applications of LLMs were tools to summarise emails, accompanied by tools to write your emails based on a short description of what you want to say. So soon we'll effectively be communicating by text message, with the LLMs acting as a sort of anti-compression in between.

My brother lives in Japan, and he recently had to write a lot of emails to the company renovating his apartment. He said that ChatGPT was a lifesaver there since at least 75% of semi-formal (i.e. between customer and company) Japanese emails is formality and filler. He just skipped all of that and ChatGPT wrote it for him.

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#53
post #52
post #36

Waiting for the LLM version of ye olden IRC hazing/trolling of: "oh you can fix that with rm -rf /" Edit: Typo

You can't any more :) You need to add --no-preserve-root

Huh, interesting, I never knew that flag was added then again I haven't tried to nuke / with rm in quite some time.

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#55

Can't speak for this tool yet, but ChatGPT has been great for this use case. Sometimes a tool doesn't have a man page, has hard to navigate docs, or whatever, "What does $flag mean in $tool" tends to work (when it doesn't hallucinate something totally wrong). One recent example: "what does -w do on curl" .. not a single top 10 result on Google mentions it in the context, but GPT3.5 nails it in two seconds complete wi…

Agreed. For me, ChatGPT has been the killer app for terminal even as someone who’s pretty comfortable in the terminal

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#56

Can't speak for this tool yet, but ChatGPT has been great for this use case. Sometimes a tool doesn't have a man page, has hard to navigate docs, or whatever, "What does $flag mean in $tool" tends to work (when it doesn't hallucinate something totally wrong). One recent example: "what does -w do on curl" .. not a single top 10 result on Google mentions it in the context, but GPT3.5 nails it in two seconds complete wi…

Agreed. For me, ChatGPT has been the killer app for terminal even as someone who’s pretty comfortable in the terminal

For me, there are multiple killer apps. One is in programming. In many cases, I work with a language I'm a bit unfamiliar with, so I ask it for idioms for things that I know a language should be able to do (like summing). Upon reading the code I see it's correct.

This used to be SO, but ChatGPT works way faster.

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#57

I use an alternative that just directly calls OpenAI using my API key. I have it mapped to the command `ai` and it works really really well. So far I've found no need for any intermediary or fancy features. It just shows the command with a (y/[N]) prompt and I can choose to run it or not. I use the first tagged version of `aicmd` before it was given an unneeded intermediary: https://github.com/atinylittleshell/aicmd/…

I did this too, way cleaner and faster imo.

Re: Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs

#59

Can't speak for this tool yet, but ChatGPT has been great for this use case. Sometimes a tool doesn't have a man page, has hard to navigate docs, or whatever, "What does $flag mean in $tool" tends to work (when it doesn't hallucinate something totally wrong). One recent example: "what does -w do on curl" .. not a single top 10 result on Google mentions it in the context, but GPT3.5 nails it in two seconds complete wi…

> It's like relying on a calculator. You still need mental math skills to know that 91 * 10 can't equal 2511. Similarly, when GPT starts hallucinating, it helps if you have a high sensitivity to smelling it out. Well, at least my calculators don't have this error rate GPT4 still does. Especially for seemingly simple things like a command flag, I have zero trust if GPT doesn't give me something that will eventually er…

A calculator isn't going to give me error. I don't need to fact check it constantly.
Post reply on HN