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

451–460 of 820 posts

Re: Gemini CLI

#451

Post by kridsdale3 »

thimabi wrote: post #446
ZeroCool2u wrote: post #287

Earlier quoted context omitted.

Personally my theory is that Gemini benefits from being able to train on Googles massive internal code base and because Rust has been very low on uptake internally at Google, especially since they have some really nice C++ tooling, Gemini is comparatively bad at Rust.

> Personally my theory is that Gemini benefits from being able to train on Googles massive internal code base But does Google actually train its models on its internal codebase? Considering that there’s always the risk of the models leaking proprietary information and security architecture details, I hardly believe they would run that risk.

Googler here.

We have a second, isolated model that has trained on internal code. The public Gemini AFAIK has never seen that content. The lawyers would explode.

Re: Gemini CLI

#452

Post by skerit »

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 tried it too, it was so bad. I got the same "revert" behaviour after only 15 minutes.

Re: Gemini CLI

#453

Post by thimabi »

kridsdale3 wrote: post #451
thimabi wrote: post #446

Earlier quoted context omitted.

> Personally my theory is that Gemini benefits from being able to train on Googles massive internal code base But does Google actually train its models on its internal codebase? Considering that there’s always the risk of the models leaking proprietary information and security architecture details, I hardly believe they would run that risk.

Googler here. We have a second, isolated model that has trained on internal code. The public Gemini AFAIK has never seen that content. The lawyers would explode.

Oh, you’re right, there are the legal issues as well.

Just out of curiosity, do you see much difference in quality between the isolated model and the public-facing ones?

Re: Gemini CLI

#454

Post by kridsdale3 »

thimabi wrote: post #453
kridsdale3 wrote: post #451

Earlier quoted context omitted.

Googler here. We have a second, isolated model that has trained on internal code. The public Gemini AFAIK has never seen that content. The lawyers would explode.

Oh, you’re right, there are the legal issues as well. Just out of curiosity, do you see much difference in quality between the isolated model and the public-facing ones?

We actually only got the “2.5” version of the internal one a few days ago so I don’t have an opinion yet.

But when I had to choose between “2.0 with Google internal knowledge” and “2.5 that knows nothing” the latter was always superior.

The bitter lesson indeed.

Re: Gemini CLI

#455

Post by jay_kyburz »

bachmeier wrote: post #162
GardenLetter27 wrote: post #99

Earlier quoted context omitted.

Google is fumbling the bag so badly with the pricing. Gemini 2.5 Pro is the best model I've used (even better than o3 IMO) and yet there's no simple Claude/Cursor like subscription to just get full access. Nevermind Enterprise users too, where OpenAI has it locked up.

> Google is fumbling the bag so badly with the pricing. In certain areas, perhaps, but Google Workspace at $14/month not only gives you Gemini Pro, but 2 TB of storage, full privacy, email with a custom domain, and whatever else. College students get the AI pro plan for free. I recently looked over all the options for folks like me and my family. Google is obviously the right choice, and it's not particularly close.

I'm a workspace subscriber, I get 4-5 questions on Gemini Pro (via gemini.google.com ) before it tells me I'm out of quota and have to switch to flash.

(Update: Oh.. I'm only on business starter, I should be on business standard. need more business!)

Re: Gemini CLI

#456

Post by jrbuhl »

fhinkel wrote: post #356
ciwchris wrote: post #230

Earlier quoted context omitted.

Using the Gemini CLI the first thing I tried to do was "Create GEMINI.md files to customize your interactions with Gemini." The command ran for about a minute before receiving a too many requests error. > You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits . Discouraging

Super weird! I've been using it the last week, and never hit the quota limit for free users. We're having some capacity issues right now, but that should not affect the quota. Would love it if you can try tomorrow or so again!

It's happening to me with API Key usage. I assume there are no Terms of Use protections on our data unless we access Gemini CLI in a paid manner?

     [API Error: {"error":{"message":"{\n  \"error\": {\n    \"code\": 429,\n    \"message\": \"Resource has been exhausted (e.g. check quota).\",\n    
  \"status\": \"RESOURCE_EXHAUSTED\"\n  }\n}\n","code":429,"status":"Too Many Requests"}}]
    Please wait and try again later. To increase your limits, request a quota increase through AI Studio, or switch to another /auth method
However, in the Google cloud console I don't see any of the quotas going above their default limits.

Re: Gemini CLI

#457

Post by ramoz »

gdudeman wrote: post #436

Review after 1 hour in: Gemini CLI does not take new direction especially well. After planning, I asked it to execute and it just kept talking about the plan. Another time when I hit escape and asked it to stop and undo the last change, it just plowed ahead. It makes a lot of mistakes reading and writing to files. Some, but by no means all, of the obsequious quotes from my first hour with the product: - “You’ve asked…

Gemini web UI is extremely apologetic and self deprecating at times.

Therefore I was not surprised to experience Gemini spiraling into an infinite loop of self-deprecation - literally it abandoned the first command and spiraled into 5-10line blocks of "i suck"

---

Right now there is one CLI that influences and stands far and beyond all others. Smooth UX, and more critical some "natural" or inherent ability to use its tools well.

Gemini can also achieve this - but i think it's clear the leader is ahead because they have a highly integrated training process with the base model and agentic tool use.

Re: Gemini CLI

#458

Post by cryptoz »

jrbuhl wrote: post #456
fhinkel wrote: post #356

Earlier quoted context omitted.

Super weird! I've been using it the last week, and never hit the quota limit for free users. We're having some capacity issues right now, but that should not affect the quota. Would love it if you can try tomorrow or so again!

It's happening to me with API Key usage. I assume there are no Terms of Use protections on our data unless we access Gemini CLI in a paid manner? [API Error: {"error":{"message":"{\n \"error\": {\n \"code\": 429,\n \"message\": \"Resource has been exhausted (e.g. check quota).\",\n \"status\": \"RESOURCE_EXHAUSTED\"\n }\n}\n","code":429,"status":"Too Many Requests"}}] Please wait and try again later. To increase your…

Yeah this exact thing is happening to me also. Minutes of runtime and only errors. I guess I’ll try again later? I have billing up and I’m Tier 1. Wouldn’t expect to hit limits like this on the first prompt.

Re: Gemini CLI

#459

Post by ramoz »

Gemini web UI is extremely apologetic and self deprecating at times. Therefore I was not surprised to experience Gemini spiraling into an infinite loop of self-deprecation - literally it abandoned the first command and spiraled into 5-10line blocks of "i suck"

---

Right now there is one CLI that influences and stands far and beyond all others. Smooth UX, and more critical some "natural" or inherent ability to use its tools well.

Gemini can also achieve this - but i think it's clear the leader is ahead because they have a highly integrated training process with the base model and agentic tool use.

Re: Gemini CLI

#460

Post by kmod »

I've found a method that gives me a lot more clarity about a company's privacy policy:

  1. Go to their enterprise site
  2. See what privacy guarantees they advertise above the consumer product
  3. Conclusion: those are things that you do not get in the consumer product
These companies do understand what privacy people want and how to write that in plain language, and they do that when they actually offer it (to their enterprise clients). You can diff this against what they say to their consumers to see where they are trying to find wiggle room ("finetuning" is not "training", "ever got free credits" means not-"is a paid account", etc)

For Code Assist, here's their enterprise-oriented page vs their consumer-oriented page:

https://cloud.google.com/gemini/docs/codeassist/security-pri...

https://developers.google.com/gemini-code-assist/resources/p...

It seems like these are both incomplete and one would need to read their overall pages, which would be something more like

https://support.google.com/a/answer/15706919?hl=en

https://support.google.com/gemini/answer/13594961?hl=en#revi...

Post reply on HN