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

761–770 of 820 posts

Re: Gemini CLI

#761

Post by oblio »

s1artibartfast wrote: post #757
oblio wrote: post #689

Earlier quoted context omitted.

The 80s were 40 years ago, though. Something can outlive its usefulness.

Local stores are better in many ways, but not the ones consumers care about: price and convenience.

Yeah, and because of those 2 words, especially "convenience", we're going to burn the planet down.

Also, did you read my original comment and miss the part about Walmart and co being predatory businesses? That's why they can keep those prices so low, because they're socializing their costs to everyone else.

Re: Gemini CLI

#763

Post by hazmazlaz »

cperry wrote: post #96
thimabi wrote: post #89

Earlier quoted context omitted.

I believe Workspace users have to pay a separate subscription to use the Gemini CLI, the so-called “Gemini for Google Cloud”, which starts at an additional 19 dollars per month [^1]. If that’s really the case, it’s very disappointing to me. I expected access to Gemini CLI to be included in the normal Workspace subscription. [^1]: https://console.cloud.google.com/marketplace/product/google/...

[edit] all lies - I got my wires crossed, free tier for Workspace isn't yet supported. sorry. you need to set the project and pay. this is WIP. Workspace users [edit: cperry was wrong] can get the free tier as well, just choose "More" and "Google for Work" in the login flow. It has been a struggle to get a simple flow that works for all users, happy to hear suggestions!

How about a binary - either you subscribe to Gemini or you don't. Rate limits or gates for higher tier models/capabilities, that you can upgrade to unlock. Think Small/Medium/Large. Anything more complicated than this is immensely annoying to both consumers and enterprise customers. For power users/nonconformists, include a pay as you go option using credits or cost per action that has access to all capabilities out of the box.

Re: Gemini CLI

#764

Post by mpalmer »

nprateem wrote: post #570
mpalmer wrote: post #413

Earlier quoted context omitted.

Take some time to understand how the technology works, and how you can configure it yourself when it comes to thinking budget. None of these problems sound familiar to me as a frequent user of LLMs.

Take some time to compare the output of Gemini vs other models instead of patronising people.

I basically only use Gemini, sorry.

Re: Gemini CLI

#765

Post by sagarm »

andyferris wrote: post #700
sagarm wrote: post #568

Earlier quoted context omitted.

Is it really that confusing? Gemini is the equivalent of ChatGPT; AI Studio is for advanced users that want to control e.g. temperature; Vertex AI is the GCP integrated API; Notebook LLM is basically personal RAG; and Jules is a developer agent. Many of these are not even remotely similar.

I guess I don’t get why this wouldn’t be Jules CLI (or Jules wouldn’t be Gemini ). So Vertex is like AWS Bedrock for GCP?

This feels a lot less "autonomous" to me than Jules, and therefore more like Gemini/ChatGPT, but I agree Jules CLI would have been a cromulent name.

Re: Gemini CLI

#766

Post by willy_k »

bsenftner wrote: post #148
cperry wrote: 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…

FWIW the fair comparison for Gemini 2.5 Pro would be o4-mini. That being said I’ve also found that Gemini is way better at getting it right on the first or second try and responding to corrections.

Re: Gemini CLI

#767

Post by Matrixik »

jswny wrote: post #664
AJ007 wrote: post #158

Earlier quoted context omitted.

Current best practice for Claude Code is to have heavy lifting done by Gemini Pro 2.5 or o3/o3pro. There are ways to do this pretty seamlessly now because of MCP support (see Repo Prompt as an example.) Sometimes you can also just use Claude but it requires iterations of planning, integration while logging everything, then repeat. I haven't looked at this Gemini CLI thing yet, but if its open source it seems like any…

Which MCPs allow you to for the heavy lifting with external models in Claude Code?

https://github.com/BeehiveInnovations/zen-mcp-server

Re: Gemini CLI

#768

Post by ibrahima »

fhinkel wrote: post #656
dcreater wrote: post #540

Earlier quoted context omitted.

Yeah how is opt out of data collection not an option? This is what they mean by don't be evil and Google is proving yet again that they truly are

Usage statistics includes "your prompts and answers", see the last paragraph in the ToS. I have no idea why legal insists we write "statistics" rather than "data".

So does that mean that if you "opt out", Google _won't_ use your code for training, even on a personal/free plan?

### 1. Is my code, including prompts and answers, used to train Google's models?

This depends entirely on the type of auth method you use.

- *Auth method 1:* Yes. When you use your personal Google account, the Gemini Code Assist Privacy Notice for Individuals applies. Under this notice, your *prompts, answers, and related code are collected* and may be used to improve Google's products, which includes model training.

### 2. What are "Usage Statistics" and what does the opt-out control?

The "Usage Statistics" setting is the single control for all optional data collection in the Gemini CLI. The data it collects depends on your account type:

- *Auth method 1:* When enabled, this setting allows Google to collect both anonymous telemetry (like commands run and performance metrics) and *your prompts and answers* for model improvement.

Does this mean that for a personal account, your data is always "collected", but the opt out may prevent your data from being used for training? Also, the question was about "code", but this addresses only addresses "prompts and answers". Is code covered under prompts? The first FAQ lists "*prompts, answers, and related code are collected*" as separate items so it's still not clear what happens to code and if there's a way to opt out from your code being used for model training IMO.

Re: Gemini CLI

#769

Post by frollogaston »

koakuma-chan wrote: post #699
wiseowise wrote: post #601

Earlier quoted context omitted.

If you even sneeze into performance discussion without providing benchmarks first – you’re a tool.

You don't have to believe me if you don't want to. But I strongly advise everyone who still uses prettier to try a formatter written in Rust, for example dprint. It's a world of difference.

If you told me the Rust-based code linter runs 10X faster, I'd believe it, but it wouldn't matter even if it were 100X.

Re: Gemini CLI

#770

Post by frollogaston »

rs186 wrote: post #149
i_love_retros wrote: post #48

Earlier quoted context omitted.

This isn't about quality products, it's about being able to say you have a CLI tool because the other ai companies have one

Eh, I can't see how your comment is relevant ti the parent thread. Creating a CLI in Go is barely more complicated than JS. Rust, probably, but people aren't asking for that.

They wrote the CLI "GUI" in React using ink, which is all JS-only. I don't know what the Golang way of doing this would be, but maybe it's harder if you want the same result.
Post reply on HN