The comment was more around how to make their approach sticky.. I feel that local SLMs can replicate what this product does.

A practitioner with more experience maybe a few percentage points more productive, but the median - grab subscription, get tool, prompt, will be mostly good enough.

Give it a try!

Output Tokens are expensive! In GPT-5.4 it's ~180 dollars per Million tokens! I've settled for brief descriptions that communicate 'why' as a result. The code is documentation after all.

https://github.com/hsaliak/sacre_bleu very rough around the edges, but it works. In the past there were apps that either behaved well, or had malicious intent, but with these LLM backed apps, you are going to see apps that want to behave well, but cannot guarantee it. We are going to see a lot of experimentation in this space until the UX settles!

This brings the Linux Kernel style patch => discuss => merge by maintainer workflow to agents. You get bisect safe patches you 'review' and provide feedback and approve.

While a SKILL could mimic this, being built in allows me to place access control and 'gate' destructive actions so the LLM is forced to follow this workflow. Overall, this works really well for me. I am able to get bisect-safe patches, and then review / re-roll them until I get exactly what I want, then I merge them.

Sure this may be the path to software factories, but it scales 'enough' for medium size projects and I've been able to build in a way that I maintain strong understanding of the code that goes in.

They mask the 429s well in Gemini-Cli - if an endpoint is rate limited, they try another, or route to another model, etc to keep service availability up.

Your experience on the 429s is consistent with mine - the 429s is the first thing they need to fix. Fix that and they have a solid model at a good price point.

I use my own coding agent (https://github.com/hsaliak/std_slop) and not being able to bring my (now cancelled) AI account with Google to it is a bummer.

I'd still use it with the Code Assist Standard license if the google cloud API subscription allows for it but I have no clarification.

Anti Gravity I understand, they are subsidizing to promote a general IDE, but I dont understand constraining the generative AI backend that Gemini CLI hits.

Finally, it's unclear what's allowed and what's not if I purchase the API access from google cloud here https://developers.google.com/gemini-code-assist/docs/overvi...

The Apache License of this product at this point is rich. Just make it closed source and close the API reference. Why have it out there?

- A bit more on mail mode https://x.com/hsaliak/status/2020022329154420830

- on the Lua integration https://x.com/hsaliak/status/2022911468262350976 (I've since disabled the recursion, not every code file is long and it seems simpler to not do it), but the rest of it is still there

- hotwords for skill activation https://x.com/hsaliak/status/2024322170353037788

Also /review and /feedback. /feedback (the non code version) opens up the LLM's last response in an editor so you can give line by line comments. Inspired by "not top posting" from mailing lists.

In my coding agent std::slop I've optimized for this workflow https://github.com/hsaliak/std_slop/blob/main/docs/mail_mode... basically the idea is that you are the 'maintainer' and you get bisect safe, git patches that you review (or ask a code reviewer skill or another agent to review). Any change re-rolls the whole stack. Git already supports such a flow and I added it to the agent. A simple markdown skill does not work because it 'forgets'. A 'github' based PR flow felt too externally dependent. This workflow is enforced by a 'patcher' skill, and once that's active, tools do not work unless they follow the enforced flow.

I think a lot of people are going to feel comfortable using agents this way rather than going full blast. I do all my development this way.

I analyzed 6k HTTP requests on the Pro account, 23% of those were hit with 429s. (Though not from Gemini-CLI, but from my own agent using code assist). The gemini-cli has a default retry backoff of 5s. That's verifiable in code, and it's a lot.

I dont touch the anti-gravity endpoint, unlike code-assist, it's clear that they are subsidizing that for user acquisition on that tool. So perhaps it's ok for them to ban users form it.

I like their models, but they also degrade. It's quite easy to see when the models are 'smart' and capacity is available, and when they are 'stupid'. They likely clamp thinking when they are capacity strapped.

Yes the models are smart, but you really cant "build things" despite the marketing if you actively beat back your users for trying. I spent a decade at Google, and it's sad to see how they are executing here, despite having solid models in gemini-3-flash and gemini-3.1