iTerm2 and AI hype overload

Published on , 1001 words, 4 minutes to read

An image of A green-haired green-eyes anime woman in a dark hacker nest with a laptop and a cup of coffee
A green-haired green-eyes anime woman in a dark hacker nest with a laptop and a cup of coffee - Kohaku XL

iTerm2 is the most popular terminal emulator for macOS machines. I've used it for years and it has gotten out of my way. It's great software. Recently an update was released that among other things includes new AI integration:

AI

  • Add AI-powered natural language command generation. Enter a prompt in the composer and select Edit > Engage Artificial Intelligence. You will need to provide an OpenAI API key since GPT costs money to use.
  • A new AI feature in the Toolbelt, "Codecierge", lets you set a goal and then walks you step-by-step to completing it by watching the terminal contents. It requires you to supply an OpenAI API key.

Here's what the first feature looks like:

Want to watch this in your video player of choice? Take this:
https://cdn.xeiaso.net/file/christine-static/video/2024/oneoff-iterm2-ai/index.m3u8

It's a text box that you can enter in a description of a command in, then it generates the command for you. It's a lot like the former GitHub Copilot for CLI, but built into your terminal, just a command-y away.

When you use this, you have your choice of the following models:

I wasn't able to get gpt-4o to work, but gpt-3.5-turbo worked fine. I'm not totally wowed by the feature, but it is a thing that exists and I'll probably use it once or twice (mainly when I'm dealing with ffmpeg commands because good god those are hard to remember). I don't think it's a killer feature, but it's a nice-to-have, I guess.

One of the main bits of feedback I've seen from people online is that iTerm2 having AI involved at all is enough to get them to want to switch away to another terminal emulator. They've cited the reason as exhaustion due to overexposure to AI hype.

AI is the current meme among investors and the tech space. Microsoft is putting an AI button on your keyboard, Slack is training AI on your messages, and OpenAI is in hot water with Scarlet Johansson. It's everywhere, and it's exhausting. Part of my job requires me to keep up with the latest advances with AI and I'm unable to. Everything happens so much.

With a lot of these AI tools comes the problem that the AI system itself is very opaque. You put in inputs, you get an output, but nobody is able to explain how or why something came out that way. There's an entire cottage industry of people finding the right combinations of words to get the AI to do something they want. It's like scrying into the unknown, but somehow with trillions of dollars on the line.

This "type the command for me" feature has caused a lot of buzz online, to the point where people I know are just flat out ripping out iTerm2 in favor of programs that don't have AI integrations in them. Hell, even the mention that a tool is going to get an AI integration has people preemptively ripping it out of their systems because of that opacity. A terminal emulator is probably also a fairly bad place to implement this because it's probably one of the most privileged programs on a developer's machine. It deals with all the secrets in the world, and the threat that it could be used to upload them all to a third party is great enough that people are willing to switch away from it sight unseen.

Aoi is wut
<Aoi>

I don't get it. It's a very optional feature that you have to:

  1. Go out of your way to enable
  2. Supply your own API key (and pay for it yourself)
  3. Enable something that is not enabled by default

Why are people reacting so strongly to this?

Cadey is aha
<Cadey>

A lot of it boils down to having this "shoved down their throats". It's the fact that it's being added to a tool without the user having the agency to decide if they want it to be added or not. There's something that can probably be said here about programs like this likely needing to be open-source so that these things can be caught and stopped sooner, but that's an entirely different conversation.

EDIT: an earlier version of this post assumed that iTerm2 was closed source. It is not. I apologize for the error. Here is an amended version of the paragraph:

A lot of it boils down to having this "shoved down their throats". It's the fact that it's being added to a tool without the user having the agency to decide if they want it to be added or not. That being said, here is the commit that added the AI feature in question. It's apparently been in development at some level for two years or so. I guess it predates most of the AI hype that's been going on lately.

I get why people wouldn't want this in their lives, I really do. I think that one of the greatest errors that was made with putting this in iTerm2 was making a big show of it, and by not letting you use local models (such as with Ollama) instead of having OpenAI be the only option.

It would be really cool if this was distributed as an optional addon with their Python API as an example of how you can extend iTerm2 in arbitrary ways. This would get a lot of the same advantages, but without the whole angry mob thing.


Facts and circumstances may have changed since publication. Please contact me before jumping to conclusions if something seems wrong or unclear.

Tags: