Live data from Hacker News

Gemini CLI

blog.google

581–590 of 820 posts

Re: Gemini CLI

#581

Earlier quoted context omitted.

I know they raised the price on our Google Workspace Standard subscriptions but don't really know what we got for that aside from Gemini integration into Google Drive etc. Does this mean I can use Gemini CLI using my Workspace entitlement? Do I get Code Assist or anything like that? (But Code Assist seems to be free on a personal G account...?) Google is fumbling with the marketing/communication - when I look at thei…

> Does this mean I can use Gemini CLI using my Workspace entitlement? No, you cannot use neither Gemini CLI nor Code Assist via Workspace — at least not at the moment. However, if you upgrade your Workspace plan, you can use Gemini Advanced via the Web or app interfaces.

Well, now I'm a mixture of disappointed and confused

I was wondering what Gemini Advanced is. I don't see any mention of a Gemini Advanced here, but there is a Gemini Pro and a Gemini Ultra: https://gemini.google/subscriptions/

I had gotten the impression that Workspace might entitle us to some API credits or something based on section 3A here where they describe how to authenticate with the API via your Workspace account https://github.com/google-gemini/gemini-cli/blob/main/docs/c... . That document does explicitly mention "Gemini Code Assist for Workspace" but I think I saw another website from Google agreeing with you and saying you can't use it with a Workspace account currently.

Yeah, this is all a mess. Time to go back to bed for six months and just continue using whatever my corporate overlords have already handed to me

Re: Gemini CLI

#582
post #400

Can't we standardize on AGENTS.md instead of all these specific CLAUDE.md and now GEMINI.md. I just symlink now to AGENTS.md

Hmm kinda makes sense to keep them separate because the agents perform differently, right?

You might want to tell Claude not to write so many comments but you might want to tell Gemini not to reach for Kotlin so much, or something.

A unified approach might be nice, but using the same prompt for all of the LLM "coding tools" is probably not going to be as nice as having prompts tailored for each specific tool.

Re: Gemini CLI

#583
It's kind of cool to see big frontier ai tools being exclusive to a terminal window. It really takes me back

Re: Gemini CLI

#584
post #364

Earlier quoted context omitted.

The root problem here lies with Apple. It's so frustrating how they take a 30% cut for the privilege of being unable to actually have a relationship with your customers. Want to do a partial refund (or a refund at all)? Want to give one month free to an existing subscriber? Tough luck. Your users are Apple's customers, not yours.

Same as a shopping centre, clothing retailer, or any other non-bazaar marketplace with its own brand and transaction processing. Apple is selling you a huge lucrative market. Customers buy Apple’s curated marketplace. Apple takes a cut for being in the middle and enabling all of this. Believe me, I would never pay for most of the apps that I did pay for via Apple if it wasn’t via their marketplace and their consumer…

The problem is that other payment processors could emerge with the same trust profiles as Apple to facilitate this transaction.

I could see Stripe doing something like this. They protect the consumer and come down hard on the merchants.

Imagine them, and maybe a few other processors, competing for this business. The fee would probably drop below 30%. To a large degree, this is the sort of arrangement credit card processors already have between their merchants and consumers and that rate is single digit percentages. Not hard to imagine Visa or MasterCard running a SaaS transaction service for a 5-10% cut.

Re: Gemini CLI

#585

Ugh, I really wish this had been written in Go or Rust. Just something that produces a single binary executable and doesn't require you to install a runtime like Node.

You mean something like this:

https://www.npmjs.com/package/pkg

or perhaps this one:

https://www.npmjs.com/package/nexe

Re: Gemini CLI

#586
post #187

Earlier quoted context omitted.

@sachinag is afk but wanted me to flag that he's on point for fixing the Cloud Dashboard - it's WIP!

Thanks Chris! "The Google Cloud Dashboard is a mess, and they haven't fixed it in years." Tell me what you want, and I'll do my best to make it happen. In the interim, I would also suggest checking out Cloud Hub - https://console.cloud.google.com/cloud-hub/ - this is us really rethinking the level of abstraction to be higher than the base infrastructure. You can read more about the philosophy and approach here: https…

Ninjaing in here: Thanks for reading this!

I’m a small time GCP customer for five or six years, and relatively tech competent, and I had a very difficult time getting Gemini code set up yesterday with Vertex API keys; finally I had to use gcloud to login from the CLI in combination with clicking a link and doing web sign on from Gemini. This frustrated me, not least because I have API direct calls to Vertex Gemini working from Aider, although I could not tell you exactly what incantation I finally used to make it work. In particular it didn’t look to me like the Gemini code app uses something like dotenv? I don’t recall now; upshot - could get it to tell me I was logged in wrong / had an oauth2 error / needed a project id at various times, but no inference.

What I wanted: to be able to go to a simple page tied to a google login and generate named API keys that can be used from anywhere to query Gemini models with a SINGLE key and environment variable kept in a .env file. I would prefer to pre-fill the account that debits by API usage. For an example, you could sign up for Anthropic API, OpenAI API, OpenRouter to see their customer flows. They are extremely simple in comparison to getting a new account (or even an old one) in shape to do metered billing for Gemini inference.

I then want this API key to work, regardless of what gcloud “knows” about me — am I logged in to a GCP account? Don’t care. What’s my current “Project?” Don’t care. What’s the difference between Vertex and Gemini? Don’t care.

As I write this, I bet a startup could be launched just offering this as a wrapper. This is surprisingly painful!

Thanks again for all the work; looking forward to seeing more out of Gemini.

Re: Gemini CLI

#587

Tried it out. 1. First authentication didn't work on my headless system, because it wants an oauth redirect to localhost - sigh. 2. Next, WebFetch isn't able to navigate github, so I had to manually dig out some references for it. 3. About 2 mins in, I just got ``` ℹ Rate limiting detected. Automatically switching from gemini-2.5-pro to gemini-2.5-flash for faster responses for the remainder of this session. ``` in a…

I got the same experience. I ran `gemini --debug` and it spit out the authentication URL at least. However I got the same `Rate limiting detected` for a simple refactoring task in a repo with 2 python files after a few minutes.

Re: Gemini CLI

#589
post #41

Hi - I work on this. Uptake is a steep curve right now, spare a thought for the TPUs today. Appreciate all the takes so far, the team is reading this thread for feedback. Feel free to pile on with bugs or feature requests we'll all be reading.

Thank you for your work on this. I spent the afternoon yesterday trying to convert an algorithm written in ruby (which I do not know) to vanilla JavaScript. It was a comedy of failing nonsense as I tried to get gpt-4.1 to help, and it just led me down pointless rabbit holes. I installed Gemini CLI out of curiosity, pointed it at the Ruby project, and it did the conversion from a single request, total time from "think…

I did something very similar last week with Claude Code, which also had good results. Good to know Gemini CLI is on the same level of power.

Re: Gemini CLI

#590
post #423

Earlier quoted context omitted.

The other difference is that reliability for the gemini api is garbage, whereas for vertex ai it is fantastic.

The key to running LLM services in prod is setting up Gemini in Vertex, Anthropic models on AWS Bedrock and OpenAI models on Azure. It's a completely different world in terms of uptime, latency and output performance.

Does OpenAI on azure still have that insane latency for content filtering? Last time I checked it added a huge # to time to first token, making azure hosting for real time scenarios impractical.
Post reply on HN