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

211–220 of 820 posts

Re: Gemini CLI

#211

Post by sysmax »

AJ007 wrote: post #158
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 "…

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…

I think, there are different niches. AI works extremely well for Web prototyping because a lot of that work is superficial. Back in the 90s we had Delphi where you could make GUI applications with a few clicks as opposed to writing tons of things by hand. The only reason we don't have that for Web is the decentralized nature of it: every framework vendor has their own vision and their own plan for future updates, so a lot of the work is figuring out how to marry the latest version of component X with the specific version of component Y because it is required by component Z. LLMs can do that in a breeze.

But in many other niches (say embedded), the workflow is different. You add a feature, you get weird readings. You start modelling in your head, how the timing would work, doing some combination of tracing and breakpoints to narrow down your hypotheses, then try them out, and figure out what works the best. I can't see the CLI agents do that kind of work. Depends too much on the hunch.

Sort of like autonomous driving: most highway driving is extremely repetitive and easy to automate, so it got automated. But going on a mountain road in heavy rain, while using your judgment to back off when other drivers start doing dangerous stuff, is still purely up to humans.

Re: Gemini CLI

#212

Post by sachinag »

cperry wrote: post #187
behnamoh wrote: post #67

Earlier quoted context omitted.

Actually, that's the reason a lot of startups and solo developers prefer non-Google solutions, even though the quality of Gemini 2.5 Pro is insanely high. The Google Cloud Dashboard is a mess, and they haven't fixed it in years. They have Vertex that is supposed to host some of their models, but I don't understand what's the difference between that and their own cloud. And then you have two different APIs depending o…

@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://cloud.google.com/blog/products/application-developme...

Re: Gemini CLI

#213

Post by __MatrixMan__ »

gnur wrote: post #88
__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…

This has changed actually, since this month you can use claude code if you have a cloud pro subscription.

Great news, thanks.

Re: Gemini CLI

#214

Post by ranuzz »

Oras wrote: post #176

Appreciate how easy it is to report a bug! I like these commands. A bit gutted by the `make sure it is not a workspace account`. What's wrong with Google prioritising free accounts vs paid accounts? This is not the first time they have done it when announcing Gemini, too.

It says in the pricing page (https://ai.google.dev/gemini-api/docs/pricing) that free usage can be used to improve products, may be for them it makes sense to beta release to free users first https://ai.google.dev/gemini-api/terms

Re: Gemini CLI

#215

Post by stpedgwdgfhgdd »

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.

When using a single terminal Pro is good enough (even with a medium-large code base). When I started working with two terminals at two different issues at the same time, i’m reaching the credit limit.

Re: Gemini CLI

#216

Post by irthomasthomas »

behnamoh wrote: post #67
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!

Actually, that's the reason a lot of startups and solo developers prefer non-Google solutions, even though the quality of Gemini 2.5 Pro is insanely high. The Google Cloud Dashboard is a mess, and they haven't fixed it in years. They have Vertex that is supposed to host some of their models, but I don't understand what's the difference between that and their own cloud. And then you have two different APIs depending o…

I just use gemini-pro via openrouter API. No painful clicking around on the cloud to find the billing history.

Re: Gemini CLI

#217

Post by tvshtr »

asadm wrote: post #44
zackify wrote: post #14

Earlier quoted context omitted.

When I was using it in cursor recently, I found it would break imports in large python files. Claude never did this. Do you have any weird issues using Gemini? I’m excited to try the cli today

not at all. these new models mostly write compiling code.

Depends on the language. It has some bugs where it replaces some words with Unicode symbols like ©. And is completely oblivious to it even when pointed out.

Re: Gemini CLI

#218

Post by behnamoh »

irthomasthomas wrote: post #216
behnamoh wrote: post #67

Earlier quoted context omitted.

Actually, that's the reason a lot of startups and solo developers prefer non-Google solutions, even though the quality of Gemini 2.5 Pro is insanely high. The Google Cloud Dashboard is a mess, and they haven't fixed it in years. They have Vertex that is supposed to host some of their models, but I don't understand what's the difference between that and their own cloud. And then you have two different APIs depending o…

I just use gemini-pro via openrouter API. No painful clicking around on the cloud to find the billing history.

but you won't get the full API capabilities of Gemini (like setting the safety level).

Re: Gemini CLI

#220

Post by iainmerrick »

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.

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.
Post reply on HN