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

iTerm2 removes AI feature from core, creates separate plugin

gitlab.com

Post reply on HN
Print view View original

111–120 of 148 posts

Re: iTerm2 removes AI feature from core, creates separate plugin

#111

Post by int_19h »

ecjhdnc2025 wrote: post #49
glhaynes wrote: post #13

People are making their whole personalities about being anti-AI. I'm personally a mix of skeptical+worried about AI; but at some point just being a reactionary ninny makes people tune out on whether there might be some truth at the core of your concern.

It's an interesting point. I too am deeply skeptical and worried, and I would be concerned people think I am "anti-AI". Which I am not -- not least because it's a sixty-plus-year-old discipline that has a development history that spans long before OpenAI and the current burst of empty calories. But if there's something I am building into my personality, it is rejecting (and calling out) grift. That is what makes me s…

> start shoehorning in LLM APIs to gain a bit of contemporary relevance

This claim implies that there's no utilitarian reason for this integration, but I don't think that is true. Shell scripting is notoriously arcane, and conversely LMs are pretty decent at unraveling that. You might notice that there are quite a few comments on the issue where users specifically state that they are using the feature and find it helpful. I was actually mildly skeptical when seeing it show up in the changelog for 3.5.0, but after giving it a try, I think this is exactly the kind of useful AI integration that I'd want to see more of (as opposed to how LLMs are being used most of the time).

Re: iTerm2 removes AI feature from core, creates separate plugin

#112

Post by int_19h »

segasaturn wrote: post #80

People claiming that the negative response to OpenAI integration into iTerm is a knee-jerk reaction by a bunch of AI haters I think are missing the point. a) Putting an LLM into iTerm introduces almost no benefit that I can think of, other than "shiny new technology", and is a waste of time and resources. I've heard some people suggest that putting an AI prompt into the terminal could be helpful for generating comman…

> you can also do the same thing by just asking ChatGPT in your browser and copying/pasting, which is what we've always done

The whole point of software to reduce this kind of tedious manual work. You can also do the same when writing code instead of using Copilot, for example, yet the latter significantly improves productivity in practice precisely because it's one hotkey away.

> More importantly, I absolutely do not want there to be any code in the terminal that writes commands for me or on my behalf.

Have you actually tried to use this feature? At no point does it submit commands directly to the terminal. It has to be explicitly enabled, for starters, by setting it up with a valid API key or custom server URL. Then you need to activate a specific command to open a textbox where you type in your input. Then you get the result back, and you have to use yet another shortcut to actually run the resulting command.

There's just no way to trigger this stuff accidentally. You have to very deliberately carry out several steps to get to the point where there's any commands being generated at all, much less actually running on your system.

> Imagine if iTerm decided to integrate NFTs and crypto, or optionally link your Meta account so you can use your terminal in Virtual Reality, would probably draw a similar negative response.

Your examples are fundamentally different in that they don't add any clear utility to the core function of the terminal, which is interacting with the shell.

Re: iTerm2 removes AI feature from core, creates separate plugin

#113

Post by soneil »

irskep wrote: post #45
Cu3PO42 wrote: post #22

I feel really sorry for the developer. I've only been a casual observer, but from my view point the community's reaction was... not great, to put it lightly. I get that a lot of us are tired of 'AI' being shoved down our throat at every possible turn. I get that a lot of us have privacy concerns. I get that maybe you don't want it in your terminal emulator. But iTerm is a free (both as in gratis and as in libre) open…

I wonder if a lot of the heated discussion is purely an emotional reaction to be hit with "AI feature onboarding" immediately after a normally-drama-free terminal emulator software update. If they had gone with a much more low-key way of notifying users of the feature, maybe folks would be more reasonable. Not that I blame the maintainers for using the approach they did, though! Usually you do want to be super obviou…

I suspect a lot of it isn't just this feature in itself, but the overall fatigue of having it shoe-horned in everywhere. I recently had to replace the Logitech software for our mice with the (hidden in a kbase) offline version because they'd added AI to what's essentially a mouse driver - two weeks later it pops up in my terminal.

I think for most people, it's not any one mole that's the problem, it's the overall game of whac-a-mole.

Re: iTerm2 removes AI feature from core, creates separate plugin

#114

Post by amanzi »

From reading the linked issue thread, it doesn't sound like this title is correct. The AI feature has not been removed from iTerm2, instead they have created an additional plugin that is required to make the AI features work.

BTW - I'm not complaining about whether AI is included or not, just pointing out that the title is incorrect. Here's the link to the plugin: https://iterm2.com/ai-plugin.html From the description: "It provides necessary functionality for iTerm2 to make network requests."

Re: iTerm2 removes AI feature from core, creates separate plugin

#115

Post by Suzuran »

notatoad wrote: post #63
irskep wrote: post #21

Earlier quoted context omitted.

Those words were definitely written through gritted teeth, but it seems to me he's being very literal. The second point in particular is exactly what the anti-AI-feature people seem to be asking for (and they are reasonable for asking for it).

> and they are reasonable for asking for it are they? their position is basically that they don't trust iterm2 to work properly, but only in regard to this specific setting. if you don't trust iterm2 to work, don't use it. if you do trust it to work, you should be able to trust that the ai feature that's off by default won't magically turn itself on.

I don't think the issue is lack of trust in iTerm2, it's lack of trust in the corporations who operate the AI services and have very strong (profit) incentives to abuse and/or exploit all data they can collect by any means necessary.

The technology isn't the problem; It's the meatbags weaponizing it in the name of a quick buck who are the problem.

Before this recent flare-up in pro/anti-AI tribalism, I have not regularly been demanded to justify my distrust of a corporation. Suddenly I feel I am demanded to justify my lack of faith in corporations who happen to have some involvement in AI. I shouldn't have to say anything beyond simply gesticulating vaguely in the direction of end-stage capitalism; The problems should be readily apparent.

Re: iTerm2 removes AI feature from core, creates separate plugin

#116

Post by soraminazuki »

Some behind the uproar was acting in extremely bad faith.

People were and still are making claims that the initial implementation can make it easy to accidentally send all of your keystrokes to OpenAI. This is not how the feature works at all. It needs explicit user interaction to use. You open the "Codesierge" toolbox and type in a question, which is a lot of clicks and typing. Yet people are posting on Mastodon and elsewhere that "accidentally" setting the API key to a non-empty value in preferences is enough to make iTerm2 send every keystroke to a third party.

Worse yet, someone pointed out in the GitLab thread that there's a call for violence against the dev by one of the participants. And sure enough, there it was on Mastodon and it's quite horrific.

iTerm2 is a gift. The dev makes his ideal terminal and we can use it if we like it. Feedbacks are fine and from my past experience welcomed, but this is something else entirely.

Re: iTerm2 removes AI feature from core, creates separate plugin

#117

Post by ThrowawayTestr »

WhereIsTheTruth wrote: post #90
mmastrac wrote: post #3

The whole drama was pretty silly, and the fact that everyone got upset that a feature that is inactive by default, consumes no processing power, memory or anything else and bullied the author of the open-source program should make everyone unhappy. This is why open-source maintainers burn out and we can't have nice things. Honestly, people, please consider the human on the other side of the toxic discourse.

Nobody likes when a company (commercial-proprietary) sneaks in your tools, either directly or indirectly Who knows if there was a deal made under the hood

What deal? You can literally just read the source code if you don't trust the developer.

Re: iTerm2 removes AI feature from core, creates separate plugin

#118

Post by ThrowawayTestr »

Suzuran wrote: post #115
notatoad wrote: post #63

Earlier quoted context omitted.

> and they are reasonable for asking for it are they? their position is basically that they don't trust iterm2 to work properly, but only in regard to this specific setting. if you don't trust iterm2 to work, don't use it. if you do trust it to work, you should be able to trust that the ai feature that's off by default won't magically turn itself on.

I don't think the issue is lack of trust in iTerm2, it's lack of trust in the corporations who operate the AI services and have very strong (profit) incentives to abuse and/or exploit all data they can collect by any means necessary. The technology isn't the problem; It's the meatbags weaponizing it in the name of a quick buck who are the problem. Before this recent flare-up in pro/anti-AI tribalism, I have not regul…

>it's lack of trust in the corporations who operate the AI services

Then don't use the feature?

Re: iTerm2 removes AI feature from core, creates separate plugin

#119

Post by ecjhdnc2025 »

int_19h wrote: post #111
ecjhdnc2025 wrote: post #49

Earlier quoted context omitted.

It's an interesting point. I too am deeply skeptical and worried, and I would be concerned people think I am "anti-AI". Which I am not -- not least because it's a sixty-plus-year-old discipline that has a development history that spans long before OpenAI and the current burst of empty calories. But if there's something I am building into my personality, it is rejecting (and calling out) grift. That is what makes me s…

> start shoehorning in LLM APIs to gain a bit of contemporary relevance This claim implies that there's no utilitarian reason for this integration, but I don't think that is true. Shell scripting is notoriously arcane, and conversely LMs are pretty decent at unraveling that. You might notice that there are quite a few comments on the issue where users specifically state that they are using the feature and find it hel…

I think your reading is fair considering what I actually wrote!

It's just not quite what I had in mind. But what I wrote is still quite scrappy; that line is missing at least an "in general" to broaden that point out beyond iTerm 2 specifically. I need to slow down a bit more.

I don't really agree with you on the LLM side of the equation, and I am bothered by the idea that this is where we're all headed. But where I think this integration is not ridiculous is in doing this at the GUI level.

There is an argument for saying "why isn't this a utility at the remote (shell) end", but of course from the perspective of OpenAI API calls being added to everything and calling out from the command line, that would be worse, because you'd be installing it everywhere.

So if it belongs anywhere (colour me wholly unconvinced) it definitely belongs somewhere within the terminal client itself.

But as I say, I don't use iTerm 2. I did take this opportunity to look at what iTerm 2 offers, out of fairness to the author, and it is obviously an impressive bit of work. Maybe when I find a need for Python scripting like that I'll come back to it.

Re: iTerm2 removes AI feature from core, creates separate plugin

#120

Post by soraminazuki »

Suzuran wrote: post #115
notatoad wrote: post #63

Earlier quoted context omitted.

> and they are reasonable for asking for it are they? their position is basically that they don't trust iterm2 to work properly, but only in regard to this specific setting. if you don't trust iterm2 to work, don't use it. if you do trust it to work, you should be able to trust that the ai feature that's off by default won't magically turn itself on.

I don't think the issue is lack of trust in iTerm2, it's lack of trust in the corporations who operate the AI services and have very strong (profit) incentives to abuse and/or exploit all data they can collect by any means necessary. The technology isn't the problem; It's the meatbags weaponizing it in the name of a quick buck who are the problem. Before this recent flare-up in pro/anti-AI tribalism, I have not regul…

No, people are saying, don't use the feature if you're not interested. It isn't hard. Don't input an API key. Don't do multiple clicks to show the "Codecierge" toolbox. Don't type in a question for the AI. In future versions, don't install the optional AI plugin. And crucially, don't act the way people did in this saga and be civil. Follow any of that, and you're fine.

People aren't demanding you anything. You are.

Post reply on HN