It looked semi-interesting, until reading this line: "So what are you waiting for? Upgrade your terminal experience with Gemini CLI today". Why does what seems to be a developer-oriented tool, need to use that awful LinkedIn/Corpospeak language, oh why?
Gemini CLI
701–710 of 820 posts
Re: Gemini CLI
#702Hi - 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.
One thing I'd really like to see in coding agents is this: As an architect, I want to formally define module boundaries in my software, in order to have AI agents adhere to and profit from my modular architecture.
Even with 1M context, for large projects, it makes sense to define boundaries These will typically be present in some form, but they are not available precisely to the coding agent. Imagine there was a simple YAML format where I could specify modules and where they can be found in the source tree, and the APIs of other modules it interacts with. Then it would be trivial to turn this into a context that would very often fit into 1M tokens. When an agent decides something needs to be done in the context of a specific module, it could then create a new context window containing exactly that module, effetively turning a large codebase into a small codebase, for which Gemini is extraordinarily effective.
Re: Gemini CLI
#703I want something like this but that can talk to my local AI servers. I'm not a fan of cloud-based AI.
I use aichat now but it's not perfect. https://github.com/sigoden/aichat
The UI on this tool is much better.
Re: Gemini CLI
#704Earlier quoted context omitted.
So, as a member of an organization who pays for google workspace with gemini, I get the message `GOOGLE_CLOUD_PROJECT environment variable not found. Add that to your .env and try again, no reload needed!` At the very least, we need better documentation on how to get that environment variable, as we are not on GCP and this is not immediately obvious how to do so. At the worst, it means that your users paying for gemi…
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/...
It probably is more powerful though. I know the $30 copilot M365 from microsoft is way better than what they offer to consumers for free. I don't have a google account so I didn't check that.
Re: Gemini CLI
#705Hi - 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.
There is one feature in Claude Code which is often overlooked and I haven't seen it in any of the other agentic tools: There is a tool called "sub-agent", which creates a fresh context windows in which the model can independently work on a clearly defined sub-task. This effectively turns Claude Code from a single-agent model to a hierarchical multi-agent model (I am not sure if the hierarchy goes to depths >2).
I wonder if it is a concious decision not to include this (I imagine it opens a lot of possibilities of going crazy, but it also seems to be the source of a great amount of Claud Code's power). I would very much like to play with this if it appears in gemini-cli
Next step would be the possibility to define custom prompts, toolsets and contexts for specific re-occuring tasks, and these appearing as tools to the main agent. Example for such a thing: create_new_page. The prompt could describe the steps one needs to create the page. Then the main agent could simply delegate this as a well-defined task, without cluttering its own context with the operational details.
Re: Gemini CLI
#706> To use Gemini CLI free-of-charge, simply login with a personal Google account to get a free Gemini Code Assist license. That free license gets you access to Gemini 2.5 Pro and its massive 1 million token context window. To ensure you rarely, if ever, hit a limit during this preview, we offer the industry’s largest allowance: 60 model requests per minute and 1,000 requests per day at no charge. If it sounds too good…
Also I have Gemini Pro, what am I paying for?
Re: Gemini CLI
#707I’ve found the experience pretty underwhelming so far. Maybe they’re under heavy load right now, but nearly every time I try to use it, it takes about 20 seconds before it automatically switches from 2.5 Pro to 2.5 Flash due to delays. Unfortunately, the Flash output just isn’t good enough.
Re: Gemini CLI
#708Earlier 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/...
So to be clear (this isn't your fault of course, this is a Google problem), as someone with my own domain for my email: * First google forced me to start paying for my email domain. * Then they increased the cost to force me to pay for AI features * Now, I can't actually use the AI features without spending even more money, I could use them if I just had a gmail address and didn't pay google. Well done Google, you've…
I use and like Fastmail.
Re: Gemini CLI
#709I’ve found the experience pretty underwhelming so far. Maybe they’re under heavy load right now, but nearly every time I try to use it, it takes about 20 seconds before it automatically switches from 2.5 Pro to 2.5 Flash due to delays. Unfortunately, the Flash output just isn’t good enough.
I think it was with the anthropic guys on Dwarkeshs podcast, but really it could have been any of the other tech podcasts with a big name AI guest, but anyway they were talking about how orgs need to make big decisions about compute allocation.
If you need to do research, pre-training, RLHF, inference for 5-10 different models across 20 different products, how do you optimally allocate your very finite compute? Weight towards research and training for better future models, or weigh towards output for happier consumers in the moment?
It would make sense that every project in deepmind is in constant war for TPU cycles.
Re: Gemini CLI
#710Earlier 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.
I implemented Google One integration in an iOS app. This comment chain is accurate. Users want to pay with Apple (like other app subscriptions) but then your “account” is inside their payments world. Which is super confusing since users (rightly) think they are dealing with their Google account.
Sounds like the analysts and product owners didn't really want to solve this problem. Instead they ticked the boxes, got the bonuses, and the devs never questioned it and just implemented it for fear of being PIPed.
I'm sure there is technically nothing that stopped you from treating this "Pay with Apple" thing as just another payment method inside the google account, except maybe additional complexity and red-tape.
Seen this many times when PMs, POs, and Devs code by features instead of trying to actually solve something. I don't even want to know what mess of a database schema is behind this monstrosity.