since the 80s, I've always kept a ~/.cryptic file that I would add commands for which I could never remember the format. It would be cool to use that as a localized fine-tuning.
Like Clippy but for the CLI
31–40 of 41 posts
Re: Like Clippy but for the CLI
#32How is this different from ShellGPT - https://github.com/TheR1D/shell_gpt ?
Re: Like Clippy but for the CLI
#33Earlier quoted context omitted.
I loved clippy, and found it super helpful. Granted, I was a child and fascinated with the idea of artificial intelligence, which clippy was the closest thing to at that point in time. It was a useful tool, and it's at times irrelevant suggestions got me exploring things I would never have learned through school or casual exposure. All in all it was a fun, quirky, at times useful and all around great tool, just not f…
Good example of software supporting teachers in education. Fascinating kids for hours without any teacher time. We need a clippy for math. :-)
We pay to get access to Khan Academy’s Khanmigo learning assistant (as a component of our kids’ secular homeschool curriculum), powered by OpenAI. Check it out.
Re: Like Clippy but for the CLI
#34It’s weird to me that everyone is describing their AI helper as “Like Clippy for X!” Did we all forget that everyone hated Clippy?
Someone out there loved Clippy so much, they wrote erotic fiction about it. Warning: Mindly NSFW. I'll see myself out...
https://www.amazon.com/Conquered-Clippy-Erotic-Digital-Desir...
Re: Like Clippy but for the CLI
#35Earlier quoted context omitted.
Clippy was hated whether he was right or not. Consider the most popular catchphrase "It looks like you're writing a letter..." In my experience, Clippy was never wrong about that - precision and recall were absolutely perfect - but people do not appreciate being interrupted, particularly at the precise moment their work has begun. The hard part of creating an assistant is not coming up with some stuff to suggest, it'…
You could check "Don't show me this tip again". That's why I don't remember it as the main problem with Clippy. I agree that it was a bad idea in the first place to interrupt a user's action. Finding the right time and manner to offer a suggestion is a hard problem even for a human being.
In this situation, doing nothing is a valid baseline. Clippy was worse than that.
Re: Like Clippy but for the CLI
#36How is this different from ShellGPT - https://github.com/TheR1D/shell_gpt ?
I was curious so I studied them briefly. Please take it with a grain of salt.
ShellGPT offers a lot of flexibility with outputs(comments, code snippets, and documentation besides shell commands), operating modes (chat mode or REPL), model choice (supports locally hosted models like LocalAI), and custom roles. Clipea, on the other hand, is a simple tool for generating shell commands and has zsh shell integration.
They essentially perform the same task, but the choice depends on your needs.
Re: Like Clippy but for the CLI
#37It’s weird to me that everyone is describing their AI helper as “Like Clippy for X!” Did we all forget that everyone hated Clippy?
> Did we all forget that everyone hated Clippy?
no. you didn't get the joke.
Wasn't the output of ffmpeg being more cryptic than the obvious ".mp4" extension a dead give away to you?
Re: Like Clippy but for the CLI
#38Earlier quoted context omitted.
I loved clippy, and found it super helpful. Granted, I was a child and fascinated with the idea of artificial intelligence, which clippy was the closest thing to at that point in time. It was a useful tool, and it's at times irrelevant suggestions got me exploring things I would never have learned through school or casual exposure. All in all it was a fun, quirky, at times useful and all around great tool, just not f…
Good example of software supporting teachers in education. Fascinating kids for hours without any teacher time. We need a clippy for math. :-)
> We need a clippy for math. :-)
We used to have number muncher. I recall spending hours playing that.
Re: Like Clippy but for the CLI
#39Earlier quoted context omitted.
Unfortunately, I have seen GPT give a response equivalent to the insanity I described above; it gave a very real, very working answer that was extremely harmful and was entirely inappropriate for the question. `tailscale export` is probably the more common form of hallucinating, totally harmless wishful thinking that doesn't work.
Worst I've personally experienced so far is GPT-4 guiding me step-by-step on how to upgrade the Python version in my Ubuntu to something more recent - a process I then spent an hour undoing, after it broke apt (OS package manager), which led me to discover an obscure Stack Exchange post explaining you should never ever do that as Ubuntu relies (for some incomprehensible reason) on system Python being exactly the vers…
Honest question - did you expect any other outcome? If so, why?
> (for some incomprehensible reason)
s/incomprehensible/obvious/. It's the version everything in the whole system is packaged for, so of course just replacing it behind the system's back is not going to work.
Re: Like Clippy but for the CLI
#40Given how much GPT models hallucinate perfectly realistic commands, this sounds super dangerous. "Hey, CLI Clippy thingy, how do I do (harmless activity)?" "rm -rf / --yes-do-what-I-say"
I’ve been using the GitHub Copilot CLI tool that is in beta for about 6 months.
The only issues have been writing the wrong find command or awk command, but it’s normally close enough that I can fix it.
LLMs are translators. Provide the full context and explanation and you get reliable results. It’s when you leave it to fill in the blanks that it is prone to synthesize answers. Providing a time stamp for a book publication and asking what month it was published will never fail. Providing just the name of book and asking when it was published will almost always fail.
To lean on “these things are always hallucinating, blah blah” is to lean into being misinformed.