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

Gemini CLI

blog.google

Post reply on HN
Print view View original

251–260 of 820 posts

Re: Gemini CLI

#251

Post by coolKid721 »

jstummbillig wrote: post #100
ed_mercer wrote: post #4

> That’s why we’re introducing Gemini CLI Definitely not because of Claude Code eating our lunch!

I find it hard to imagine that any of the major model vendors are suffering from demand shortages right now (if that's what you mean?) If you mean: This is "inspired" by the success of Claude Code. Sure, I guess, but it's also not like Claude Code brought anything entirely new to the table. There is a lot of copying from each other and continually improving upon that, and it's great for the users and model providers…

ai power users will drop shit immediately, yes they probably have long term contracts with companies but anyone seriously engaged has switched to claude code now (probably including many devs AT openai/google/etc.)

If you don't think claude code is just miles ahead of other things you haven't been using it (or well)

I am certain they keep metrics on those "power users" (especially since they probably work there) and when everyone drops what they were using and moves to a specific tool that is something they should be careful of.

Re: Gemini CLI

#252

Post by sitkack »

tln wrote: post #120
iainmerrick wrote: post #30

Earlier quoted context omitted.

Looks like you could make a standalone executable with Bun and/or Deno: https://bun.sh/docs/bundler/executables https://docs.deno.com/runtime/reference/cli/compile/ Note, I haven't checked that this actually works, although if it's straightforward Node code without any weird extensions it should work in Bun at least. I'd be curious to see how the exe size compares to Go and Rust!

A Bun "hello world" is 58Mb Claude also requires npm, FWIW.

That is point not a line. An extra 2MB of source is probably a 60MB executable, as you are measuring the runtime size. Two "hello worlds" are 116MB? Who measures executables in Megabits?

Re: Gemini CLI

#253

Post by nickysielicki »

iaresee wrote: post #104

Whoa. Who at Google thought providing this as an example of how to test your API key was a good idea? https://imgur.com/ZIZkLU7 This is shown at the top of the screen in https://aistudio.google.com/apikey as the suggested quick start for testing your API key out. Not a great look. I let our GCloud TAM know. But still.

it's wrapped in TLS, is ok.

Re: Gemini CLI

#254

Post by imiric »

Jayakumark wrote: post #82

Whether any CLI interactions are used to train the model or no ?

Ha. It would be naive to think that a CLI tool from an adtech giant won't exploit as much data as it can collect.

Re: Gemini CLI

#255

Post by rudedogg »

ipsum2 wrote: post #243

If you use this, all of your code data will be sent to Google. From their terms: https://developers.google.com/gemini-code-assist/resources/p... When you use Gemini Code Assist for individuals, Google collects your prompts, related code, generated output, code edits, related feature usage information, and your feedback to provide, improve, and develop Google products and services and machine learning technologies. To…

Insane to me there isn’t even an asterisk in the blog post about this. The data collection is so over the top I don’t think users suspect it because it’s just absurd. For instance Gemini Pro chats are trained on too.

If this is legal, it shouldn’t be.

Re: Gemini CLI

#256

Post by iainmerrick »

MobiusHorizons wrote: post #227
iainmerrick wrote: post #220

Earlier quoted context omitted.

What's a typical Go static binary size these days? Googling around, I'm seeing wildly different answers -- I think a lot of them are outdated.

It depends a lot on what the executable does. I don’t know the hello world size, but anecdotally I remember seeing several go binaries in the single digit megabyte range. I know the code size is somewhat larger than one might expect because go keeps some type info around for reflection whether you use it or not.

Ah, good point. I was just wondering about the fixed overhead of the runtime system -- mainly the garbage collector, I assume.

Re: Gemini CLI

#257

Post by sebzim4500 »

Workaccount2 wrote: post #114
__MatrixMan__ wrote: post #85

Earlier quoted context omitted.

Anthropic is the same. Unless it has changed within the last few months, you can subscribe to Claude but if you want to use Claude Code it'll come out of your "API usage" bucket which is billed separately than the subscription. Some jerk has learned that we prefer CLI things and has come to the conclusion that we should therefore pay extra for them. Workaround is to use their GUI with some MCPs but I dislike it becau…

I think it is pretty clear that these $20/subs are loss leaders, and really only meant to get regular people to really start leaning on LLMs. Once they are hooked, we will see what the actual price of using so much compute is. I would imagine right now they are pricing their APIs either at cost or slightly below.

I'm sure that there are power users who are using much more than $20 worth of compute, but there will also be many users who pay but barely use the service.

Re: Gemini CLI

#258

Post by crazylogger »

wohoef wrote: post #135

A few days ago I tested Claude Code by completely vibe coding a simple stock tracker web app in streamlit python. It worked incredibly well, until it didn't. Seems like there is a critical project size where it just can't fix bugs anymore. Just tried this with Gemini CLI and the critical project size it works well for seems to be quite a bit bigger. Where claude code started to get lost, I simply told Gemini CLI to "…

Ask the AI to document each module in a 100-line markdown. These should be very high level, don't contain any detail, but just include pointers to relevant files for AI to find out by itself. With a doc as the starting point, AI will have context to work on any module.

If the module just can't be documented in this way in under 100 lines, it's a good time to refactor. Chances are if Claude's context window is not enough to work with a particular module, a human dev can't either. It's all about pointing your LLM precisely at the context that matters.

Re: Gemini CLI

#259

Post by alpb »

Are there any LLMs that offer ZSH plugins that integrate with command history, previous command outputs, system clipboard etc to assist writing the next command? Stuff like gemini/copilot CLI don't feel particularly useful to me. I'm not gonna type "?? print last 30 lines of this file"

Re: Gemini CLI

#260

Post by tmaly »

iandanforth wrote: post #15

I love how fragmented Google's Gemini offerings are. I'm a Pro subscriber, but I now learn I should be a "Gemini Code Assist Standard or Enterprise" user to get additional usage. I didn't even know that existed! As a run of the mill Google user I get a generous usage tier but paying them specifically for "Gemini" doesn't get me anything when it comes to "Gemini CLI". Delightful!

I was just trying to figure out if I get anything as a pro user. Thank you, you answered my question.

This is very confusing how they post about this on X, you would think you get additional usage. Messaging is very confusing.

Post reply on HN