Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

5 Things to Try with Gemini 3 Pro in Gemini CLI

developers.googleblog.com

Post reply on HN
Print view View original

31–40 of 48 posts

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#31

Post by Oras »

cortesoft wrote: post #21
recitedropper wrote: post #5

Nice, without this thread I would never have known Gemini 3 released today. Going to download Gemini CLI right now™ and see how it performs™ against Cursor, Claude Code, Aider, OpenCode, Droid, Warp, Devin, and ForgeCode.

There are currently 6 front page posts about Gemini 3 being released today.

5 things to try (if you can try). They require ultra subscription

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#33

Post by belter »

cortesoft wrote: post #21
recitedropper wrote: post #5

Nice, without this thread I would never have known Gemini 3 released today. Going to download Gemini CLI right now™ and see how it performs™ against Cursor, Claude Code, Aider, OpenCode, Droid, Warp, Devin, and ForgeCode.

There are currently 6 front page posts about Gemini 3 being released today.

And I would like to know why mods dont condensate them as duplicates...

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#34

Post by tekacs »

cortesoft wrote: post #21
recitedropper wrote: post #5

Nice, without this thread I would never have known Gemini 3 released today. Going to download Gemini CLI right now™ and see how it performs™ against Cursor, Claude Code, Aider, OpenCode, Droid, Warp, Devin, and ForgeCode.

There are currently 6 front page posts about Gemini 3 being released today.

I'm pretty sure that's the joke the GP is making.

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#37

Post by nateb2022 »

RealityVoid wrote: post #30
nateb2022 wrote: post #28

Earlier quoted context omitted.

Considering a lot of people will be using Gemini on fullstack or frontend applications, it doesn't make sense to write the CLI in Rust and integrate with JS/TS separately, as opposed to writing it in TypeScript so that you can directly work with packages within the ecosystem designed for that ecosystem.

Excuse my ignorance, but... What? It runs cli commands, why would the language it's written in matter for the integration? What am I missing here?

From a practicality standpoint, writing in TS allows you to execute arbitrary JS in-process with a simple exec() call; I have no doubt they'll use this to more deeply integrate agents with existing codebases in the near future. E.g. agents rather than just reading the code, will be able to directly import the data structures themselves, use libraries within the JS/TS ecosystem to parse code into an AST, and execute in-process test harnesses to validate behavior while editing.

And the MCP field is already pretty heavily saturated with TypeScript and JSONSchema, so using TS for it is a very ergonomic experience. Also since it's written in TypeScript, it's much more easy to integrate it with editors like VSCode (or Google's new Antimatter) which are built on top of Electron.

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#38

Post by RealityVoid »

nateb2022 wrote: post #37
RealityVoid wrote: post #30

Earlier quoted context omitted.

Excuse my ignorance, but... What? It runs cli commands, why would the language it's written in matter for the integration? What am I missing here?

From a practicality standpoint, writing in TS allows you to execute arbitrary JS in-process with a simple exec() call; I have no doubt they'll use this to more deeply integrate agents with existing codebases in the near future. E.g. agents rather than just reading the code, will be able to directly import the data structures themselves, use libraries within the JS/TS ecosystem to parse code into an AST, and execute i…

Are they using it this way? I think if you have access to the cli you can do whatever you want, and it already does use tools and use libraries and parse code. It's just using the cli. Not to mention it's much better this way because I can see it doing all these things. I can see what commands it wants to run and it asks me about it.

Re: 5 Things to Try with Gemini 3 Pro in Gemini CLI

#40

Post by thomasm6m6 »

https://github.com/google-gemini/gemini-cli/blob/release/v0....

> For Google AI Ultra subscribers and paid Gemini and Vertex API key holders, Gemini 3 Pro is already available and ready to enable. For everyone else, we're gradually expanding access through a waitlist.

So, not available yet. Tried with a free API key and I did not have access. I do have access on a paid API key, but I'd rather not use that with an agent. The rate limits page the docs link to currently has no info on gemini-3-pro rate limits. Seems to me this is really only for users on the $200/mo subscription plan. Somewhat odd, given the model is already GA in every other coding agent as I understand

Post reply on HN