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

Show HN: Get answers for shell commands from GPT3 from your terminal

github.com

Post reply on HN
Print view View original

61–70 of 97 posts

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#61

Post by camel-cdr »

peddling-brink wrote: post #50
Calzifer wrote: post #16

Bash / Shell is one of the last things I would trust a typical AI considering how much bad shell code/examples exist out there. (it always surprise me how many unquoted variables exist in most shell scripts; quoting fixes many problems, doesn't hurt and still developers are often to lazy to do it) The example in the project readme is imo already a bad example. $ ai ask "Check process running on port" Answer Command i…

The other alternative is the top result for the Google search of that question. It's not clear to me that this tool is a win over that method.

I've got a shell alias that does a web search with lynx, so I can just type: "? which process uses port x" And quickly find a result, that provably has a better explanation attaches to it than when asking GPT3.

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#62

Post by Calzifer »

malfist wrote: post #52
Calzifer wrote: post #16

Bash / Shell is one of the last things I would trust a typical AI considering how much bad shell code/examples exist out there. (it always surprise me how many unquoted variables exist in most shell scripts; quoting fixes many problems, doesn't hurt and still developers are often to lazy to do it) The example in the project readme is imo already a bad example. $ ai ask "Check process running on port" Answer Command i…

Does it matter if lsof is slower than ss? Somebody asking this to the AI is going to run it once, maybe twice. What's an extra second? The answer doesn't have to be perfect, it just as to be good enough. I could see this tool being incredibly handy for working with tar

> Does it matter if lsof is slower than ss?

Not really. I just mentioned it because it was notably slower than ss. I did not actually measured it, just saw it when trying the example.

From my 4 points I wouldn't hold the first two alone against an AI driven suggestion. Only the last two, while not horrible bad or severe or anything, are (imo) notable downsides compared to the typical ss/netstat approach.

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#63

Post by rmeby »

abhagsain wrote: post #18
dmortin wrote: post #15

Do I have to give my phone number to OpenAI to use this? I don't see why they require it. I wanted to give it a try, but no thanks.

Yeah, asking for number is too much but I think they need to it prevent spam/misuse because they offer you free credits to try out the model.

It would be nice if they let you forgo the credits to sign up without a phone number.

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#66

Post by visarga »

moffkalast wrote: post #37
bheadmaster wrote: post #7

I personally don't like the concept of having my terminal send my commands to a remote service, so I'll pass. Hopefully an open source model comes around soon so stuff like this can be implemented locally.

Sure, as long as you've got 350 GB of VRAM to load it.

It's just 12B parameters, not 175B. You can probably use int16 or int8.

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#67

Post by still_grokking »

synu wrote: post #59
plugin-baby wrote: post #55

Earlier quoted context omitted.

Safe is an ambiguous word!

Perhaps the next most important feature of AI will be the ability to ask follow up / clarifying questions.

Not even "NI" (natural intelligence) is able to do that reliably.

People and AI seem to prefer assuming things.

Most of the time wrong things…

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#69

Post by still_grokking »

malfist wrote: post #52
Calzifer wrote: post #16

Bash / Shell is one of the last things I would trust a typical AI considering how much bad shell code/examples exist out there. (it always surprise me how many unquoted variables exist in most shell scripts; quoting fixes many problems, doesn't hurt and still developers are often to lazy to do it) The example in the project readme is imo already a bad example. $ ai ask "Check process running on port" Answer Command i…

Does it matter if lsof is slower than ss? Somebody asking this to the AI is going to run it once, maybe twice. What's an extra second? The answer doesn't have to be perfect, it just as to be good enough. I could see this tool being incredibly handy for working with tar

Why do you think the spit out results won't end up in shell scripts?

I've heard people are even copy-pasting stuff from Stackoverflow into production code without fully understanding the code they're copying.

Re: Show HN: Get answers for shell commands from GPT3 from your terminal

#70

Post by visarga »

rmeby wrote: post #63
abhagsain wrote: post #18

Earlier quoted context omitted.

Yeah, asking for number is too much but I think they need to it prevent spam/misuse because they offer you free credits to try out the model.

It would be nice if they let you forgo the credits to sign up without a phone number.

Then they ask for your card info.
Post reply on HN