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

551–560 of 820 posts

Re: Gemini CLI

#551

Post by FL410 »

fhinkel wrote: post #490
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…

I appreciate the effort here, but I’m still confused. Is my $250/mo “ultra” plan considered personal and still something you train on?

Re: Gemini CLI

#552

Post by luckydata »

mulmboy wrote: post #546

I gave it a shot just now with a fairly simple refactor. +19 lines, -9 lines, across two files. Totally ballsed it up. Defined one of the two variables it was meant to, referred to the non-implemented one. I told it "hey you forgot the second variable" and then it went and added it in twice. Added comments (after prompting it to) which were half-baked, ambiguous when read in context. Never had anything like this with…

I noticed a significant degradation of Gemini's coding abilities in the last couple checkpoints of 2.5. the benchmarks say it should be better but it doesn't jive with my personal experience.

Re: Gemini CLI

#553

Post by data-ottawa »

ZeroCool2u wrote: post #287
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…

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.

Tangental, but I worry that LLMs will cause a great stagnation in programming language evolution, and possibly a bunch of tech.

I've tried using a few new languages and the LLMs would all swap the code for syntactically similar languages, even after telling them to read the doc pages.

Whether that's for better or worse I don't know, but it does feel like new languages are genuinely solving hard problems as their raison d'etre.

Re: Gemini CLI

#554

Post by data-ottawa »

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…

Does /compact help with this? I ran out of context with claude code for the first time today, so looking for any tips.

I'm trying to get better at the /resume and memories to try and get more value out of the tool.

Re: Gemini CLI

#555

Post by WXLCKNO »

kridsdale3 wrote: post #445
WXLCKNO wrote: post #193

Earlier quoted context omitted.

You guys should try my AGI test. It's easy, you just ask the best Google Model to create a script that outputs the number of API calls made to the Gemini API in a GCP account. 100% fail rate so far.

To be fair, no human can do this either.

I laughed very hard at this lol.

It's so insanely unintuitive.

Re: Gemini CLI

#556

Post by boston_clone »

bachmeier wrote: post #434
boston_clone wrote: post #267

Earlier quoted context omitted.

I'd really like to hear your own personal perspective on the topic instead of a regurgitation of an LLM.

> instead of a regurgitation of an LLM Copilot is stating the plans for its own services are confusing. Summarizing it as "regurgitation of an LLM" doesn't adequately capture the purpose of the post.

To be frank, no one here cares what copilot has to say on the matter.

Re: Gemini CLI

#558

Post by sagarpatil »

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…

You might want to give this a try: https://github.com/opencode-ai/opencode

Re: Gemini CLI

#559

Post by fastball »

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…

Kinda a tragedy of the commons situation. Everyone wants to use these tools that must be trained on more and more code to get better, but nobody wants it to be trained on their code. Bit silly imo.

Re: Gemini CLI

#560

Post by dkdcio »

nikcub wrote: post #442
sergiotapia wrote: post #405

Gemini CLI wanted to run `git log` and I accidentally hit "Yes, you can call git without confirmation" and I just realized the AI may decide to git push or something like that on it's own. How do I reset permissions so it always asks again for `git` invocations? Thanks!

This is where the fine-grained permissions of MCP and ability to disable individual tools win over calling cli tools

you can achieve the same thing with CLI tools (see `--allowedTools`): https://docs.anthropic.com/en/docs/claude-code/cli-reference...
Post reply on HN