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

531–540 of 820 posts

Re: Gemini CLI

#531

Post by asadm »

_zoltan_ wrote: post #179
asadm wrote: post #12

I have been using this for about a month and it’s a beast, mostly thanks to 2.5pro being SOTA and also how it leverages that huge 1M context window. Other tools either preemptively compress context or try to read files partially. I have thrown very large codebases at this and it has been able to navigate and learn them effortlessly.

what's your workflow?

i guess one core idea is to point it to an entrypoint or some part of code you are planning to touch. instead of asking it to load up every file etc. and then figure out the control flow.

Re: Gemini CLI

#532

Post by asadm »

leoh wrote: post #526
_zoltan_ wrote: post #179

Earlier quoted context omitted.

what's your workflow?

+1 I have not found Gemini 2.5 better than Claude's latest models -- different and better at some things, but not better in general; and in general I have found Gemini 2.5 Pro to be worse at dealing with large codebases despite its huge context window. So I too am quite curious about the workflow here.

the core idea is to not use up all of context for files but instead sessions go longer before becoming a useless pursuit ie. more turns possible with larger context window

Re: Gemini CLI

#533

Post by sachinag »

behnamoh wrote: post #430
dieortin wrote: post #421

Earlier quoted context omitted.

AFAIK you can very easily get an API key from AI studio without creating any cloud project

read my comment above. G Studio API is limited.

Ah I think I see based on the other comment but just to confirm - you want to use Vertex provided Gemini API endpoints without having to create a Google Cloud project. Is that correct? (I’m just trying to get as precise about the problem statement and what success looks like - that helps me figure out a path to the best solution.)

Appreciate the feedback!

Re: Gemini CLI

#534

Post by shpat »

nikcub wrote: post #423
fooster wrote: post #205

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.

Have you had any luck getting your Claude quota bumped on Bedrock? I tried working through AWS support but got nowhere. Gave up and used Vertex + Gemini

Re: Gemini CLI

#535

Post by devinprater »

I wish the menus were more accessible to screen readers on Windows Terminal, Powershell. NVDA just says "blank" when I arrow through, for example, the authorization choices.

Re: Gemini CLI

#536

Post by noisy_boy »

joelm wrote: post #274

Been using Claude Code (4 Opus) fairly successfully in a large Rust codebase, but sometimes frustrated by it with complex tasks. Tried Gemini CLI today (easy to get working, which was nice) and it was pretty much a failure. It did a notably worse job than Claude at having the Rust code modifications compile successfully. However, Gemini at one point output what will probably be the highlight of my day: "I have made a…

I asked it to do a comparatively pedestrian task: write a script to show top 5 google searches.

First it did the search itself and then added "echo" for each of them - cute

Then it tried to use pytrends which didn't go anywhere

Then it tried some other paid service which also didn't go anywhere

Then it tried some other stuff which also didn't go anywhere

Finally it gave up and declared failure.

It will probably be useful as it can do the modify/run loop itself with all the power of Gemini but so far, underwhelming.

Re: Gemini CLI

#537

Post by cperry »

kridsdale3 wrote: post #447
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.

Congrats on your success. May you all be promoted and may your microkitchens be stocked.

thank you kind stranger! may gemini only return you perfection on the first response.

Re: Gemini CLI

#538

Post by drewbitt »

mpeg wrote: post #190
qsort wrote: post #43

Earlier quoted context omitted.

Projects like this have to update frequently, having a mechanism like npm or pip or whatever to automatically handle that is probably easier. It's not like the program is doing heavy lifting anyway, unless you're committing outright programming felonies there shouldn't be any issues on modern hardware. It's the only argument I can think of, something like Go would be goated for this use case in principle.

You'd think that, but a globally installed npm package is annoying to update, as you have to do it manually and I very rarely need to update other npm global packages so at least personally I always forget to do it.

I used to also have outdated versions until I used mise. `mise use -g npm:@google/gemini-cli` and now `mise up` will update it. cargo, pip etc too.

Re: Gemini CLI

#539

Post by Aeolun »

Well, I've tried it, and I'm not impressed. Gemini used to be pretty good, and I like the context size, but my attempts to use the Gemini client resulted in:

1. The thing going in a circle trying to fix a bug by persistently trying different permutations of an API interface it never bothered to check the definition of. Isn't that why it's internet connected?

2. When I asked it to just analyze instead of change stuff. It just hung for 20 minutes giving me responses saying that gemini-2.5-pro was slow, and that it was switching to 2.5-flash, with no other output to indicate what it was doing other than those cute scrolling messages that mean nothing.

At least in Claude it's clear that the messages mean nothing, because they're clearly generic. Gemini gives you the impression the status messages mean something since they're sort of related to the topic being worked on.

Re: Gemini CLI

#540

Post by dcreater »

ipsum2 wrote: post #518
fhinkel wrote: post #490

Earlier quoted context omitted.

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…

I think you did a good job CYA on this, but what people were really looking for was a way to opt-out of Google collecting code, similar to the opt-out process for the IDE is available.

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
Post reply on HN