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

481–490 of 820 posts

Re: Gemini CLI

#481

Post by jiggawatts »

bilalq wrote: post #364
krferriter wrote: post #340

Earlier quoted context omitted.

I subscribed to Google One through the Google Photos iOS app because I wanted photos I took on my iPhone to be backed up to Google. When I switched to Android and went into Google One to increase my storage capacity in my Google account, I found that it was literally impossible, because the subscription was tied to my iCloud account. I even got on a line with Google Support about it and they told me yeah it's not eve…

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 protections.

There is no counterfactual scenario where you and millions(!) of other ISVs get 100% of the same money without Apple.

What’s difficult to understand about these business relationships?

Re: Gemini CLI

#482

Post by frollogaston »

iainmerrick wrote: post #256
MobiusHorizons wrote: post #227

Earlier quoted context omitted.

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.

The Golang runtime is big enough by itself that it makes a real difference from some WASM applications, and people are using Rust instead purely because of that.

Re: Gemini CLI

#483

Post by happycube »

ipsum2 wrote: post #389
FL410 wrote: post #352

Earlier quoted context omitted.

To be honest this is by far the most frustrating part of the Gemini ecosystem, to me. I think 2.5 pro is probably the best model out there right now, and I'd love to use it for real work, but their privacy policies are so fucking confusing and disjointed that I just assume there is no privacy whatsoever. And that's with the expensive Pro Plus Ultra MegaMax Extreme Gold plan I'm on. I hope this is something they're wo…

In my own experience, 2.5 Pro 03-26 was by far the best LLM model at the time. The newer models are quantized and distilled (I confirmed this with someone who works on the team), and are a significantly worse experience. I prefer OpenAI O3 and o4-mini models to Gemini 2.5 Pro for general knowledge tasks, and Sonnet 4 for coding.

Gah, enforced enshittification with model deprecation is so annoying.

Re: Gemini CLI

#485

Post by Karrot_Kream »

mhb wrote: post #10
poszlem wrote: post #7

The killer feature of Claude Code is that you can just pay for Max and not worry about API billing. It lets me use it pretty much all the time without stressing over every penny or checking the billing page. Until they do that - I'm sticking with Claude.

How does that compare to using aider with Claude models?

Aider and Claude Code/Gemini CLI agentic stuff operate differently.

You can think of Aider as being a semi-auto LLM process. First you ask it to do something. It goes through a generate -> reflect -> refine loop until it feels like it has achieved the goal you give it. Aider has a reflection limit so it'll only do this loop a limited number of times and then it will add/remove the code that it deems fit. Then it'll give you instructions to run. You can run those instructions (e.g. to actually run a script) and then append the results from the run into the context to get it to fix any issues, but this is optional. What you send in the context and what you ask the models to do are in your hands. This makes iteration slower and the LLM does less but it also can potentially keep costs lower depending on what you delegate to the LLM and how often you iterate with it.

Claude Code, Codex, and I suspect Gemini CLI on the other hand will autonomously run your code then use the output to continue refining its approach autonomously until the goal is reached. This can consume many more tokens, potentially, than hand guiding Aider, because its potential for iteration is so much longer. But Claude Code and the like also need a lot less direction to make progress. You can, for example, ask it to do a big refactor and then just leave to lunch and come back to see if the refactor is done. Aider will require babying the whole way.

Re: Gemini CLI

#486

Post by frollogaston »

evilduck wrote: post #87
jstummbillig wrote: post #61

Earlier quoted context omitted.

It feels like you are creating a considerable fraction of the pain by taking offense with simply using npm.

As a longtime user of NPM but overall fan of JS and TS and even its runtimes, NPM is a dumpster fire and forcing end users to use it is brittle, lazy, and hostile. A small set of dependencies will easily result in thousands (if not tens of thousands) of transitive dependency files being installed. If you have to run end point protection that will blast your CPU with load and it makes moving or even deleting that fold…

I ran the npm install command in their readme, it took a few seconds, then it worked. Subsequent runs don't have to redownload stuff. It's 127MB, which is big for an executable but not a real problem. Where is the painful part?

Re: Gemini CLI

#487

Post by macNchz »

agotterer wrote: post #286
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 "…

I wonder how much of this had to do with the context window size? Gemini’s window is 5x larger than Cladue’s. I’ve been using Claude for a side project for the past few weeks and I find that we really get into a groove planning or debugging something and then by the time we are ready to implement, we’ve run out of context window space. Despite my best efforts to write good /compact instructions, when it’s ready to ro…

I definitely think the bigger context window helps. The code quality quite visibly drops across all models I've used as the context fills up, well before the hard limit. The editor tooling also makes a difference—Claude Code pollutes its own context window with miscellaneous file accesses and tool calls as it tries to figure out what to do. Even if it's more manual effort to manage the files that are in-context with Aider, I find the results to be much more consistent when I'm able to micromanage the context.

Approaching the context window limit in Claude Code, having it start to make more and worse mistakes, then seeing it try to compact the context and keep going, is a major "if you find yourself in a hole, stop digging" situation.

Re: Gemini CLI

#488

Post by cperry »

atonse wrote: post #311

This is all very cool, but I hate to be the "look at the shiny lights" guy... How did they do that pretty "GEMINI" gradient in the terminal? is that a thing we can do nowadays? It doesn't seem to be some blocky gradient where each character is a different color. It's a true gradient. (yes I'm aware this is likely a total clone of claude code, but still am curious about the gradient)

we went through several versions of this, it was the second most fun part after authoring the witty loading phrases.

Re: Gemini CLI

#489

Post by cperry »

jonbaer wrote: post #245

-y, --yolo Automatically accept all actions (aka YOLO mode, see https://www.youtube.com/watch?v=xvFZjo5PgG0 for more details)? [boolean] [default: false]

:) thank you for discovering our extensive documentation on this valued feature

Re: Gemini CLI

#490

Post by fhinkel »

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…

Hey all, This is a really great discussion, and you've raised some important points. We realize the privacy policies for the Gemini CLI were confusing depending on how you log in, and we appreciate you calling that out.

To clear everything up, we've put together a single doc that breaks down the Terms of Service and data policies for each account type, including an FAQ that covers the questions from this thread.

Here’s the link: https://github.com/google-gemini/gemini-cli/blob/main/docs/t...

Thanks again for pushing for clarity on this!

Post reply on HN