Earlier quoted context omitted.
Are we getting billed for these? The billing is so very not transparent.
Copilot definitely bills you for all the errors.
Gemini appears to bill random amounts for reasons nobody knows.
Gemini CLI tips and tricks for agentic coding
71–80 of 152 posts
Re: Gemini CLI tips and tricks for agentic coding
#72Gemini CLI at this stage isn't good at complex coding tasks (vs. Claude Code, Codex, Cursor CLI, Qoder CLI, etc.). Mostly because of the simple ReAct loop, compounded by relatively weak tool calling capability of the Gemini 2.5 Pro model. > I haven't tried complex coding tasks using Gemini 3.0 Pro Preview yet. I reckon it won't be materially different. Gemini CLI is open source and being actively developed, which is…
> I haven't tried complex coding tasks using Gemini 3.0 Pro Preview yet. I reckon it won't be materially different.
In my limited testing, I found that Gemini 3 Pro struggles with even simple coding tasks. Sure, I haven't tested complex scenarios yet and have only done so via Antigravity. But it is very difficult to do that with the limited quota it provides. Impressions here - https://dev.amitgawande.com/2025/antigravity-problem
Re: Gemini CLI tips and tricks for agentic coding
#73How many of these 30 tips can replaced by Tip 8: tell Gemini to read the tips and update its own prompt?
Re: Gemini CLI tips and tricks for agentic coding
#74I am not doing any of this. It becomes obsolete in literally weeks, and it also doesn't work 80% of the time. Like why write a mcp server for custom tasks when I don't know if the llm is going to reliably call it. My rule for AI has been steadfast for months (years?) now. I write (myself, not AI because then I spend more time guiding the AI instead of thinking about the problem) documentation for myself (templates, c…
I agree. Software development is on an ascent to a new plateau. We have not reached that yet. Any skill that is built up now is at best built on a slope.
Re: Gemini CLI tips and tricks for agentic coding
#75I am not doing any of this. It becomes obsolete in literally weeks, and it also doesn't work 80% of the time. Like why write a mcp server for custom tasks when I don't know if the llm is going to reliably call it. My rule for AI has been steadfast for months (years?) now. I write (myself, not AI because then I spend more time guiding the AI instead of thinking about the problem) documentation for myself (templates, c…
A perspective which has helped me is viewing LLM-based offerings strictly as statistical document generators, whose usefulness is entirely dependent upon their training data set plus model evolution, and whose usage is best modeled as a form of constraint programming[0] lacking a formal (repeatable) grammar. As such, and when considering the subjectivity of natural languages in general, the best I hope for when using them are quick iterations consisting of refining constraint sentence fragments.
Here is a simple example which took 4 iterations using Gemini to get a result requiring no manual changes:
# Role
You are an expert Unix shell programmer who comments their code and organizes their code using shell programming best practices.
Create a bash shell script which reads from standard input text in Markdown format and prints all embedded hyperlink URL's.
The script requirements are:
- MUST exclude all inline code elements
- MUST exclude all fenced code blocks
- MUST print all hyperlink URL's
- MUST NOT print hyperlink label
- MUST NOT use Perl compatible regular expressions
- MUST NOT use double quotes within comments
- MUST NOT use single quotes within comments
For reference, a hand-written script satisfying the above (excluding comments for brevity) could look like:
#!/usr/bin/env bash
perl -ne 'print unless /^```/ ... /^```/' |
sed -e 's/`[^`]*`//g' |
egrep -o '\[.+?\]\(.+?\)' |
sed -e 's/^.*(//' -e 's/)$//'
Re: Gemini CLI tips and tricks for agentic coding
#76All these tips and tricks just to get out-coded by some guy rawdogging Copilot in VS Code.
It’s inferior but copilot is even more inferior to it. I used it again recently just to see after cursor And Claude code. It’s laughably bad. Almost like they don’t care.
Re: Gemini CLI tips and tricks for agentic coding
#77Notable re author: “Addy Osmani is an Irish Software Engineer and leader currently working on the Google Chrome web browser and Gemini with Google DeepMind. A developer for 25+ years, he has worked at Google for over thirteen years, focused on making the web low-friction for users and web developers. He is passionate about AI-assisted engineering and developer tools. He previously worked on Fortune 500 sites. Addy is…
He's published 11 books in the past 5 years? Is he using AI assisted writing, too?
Some parts of the books are based on expended versions of blog posts.
Re: Gemini CLI tips and tricks for agentic coding
#78I love the model, hate the tool. I’ve taken complex stuff and given it to Gemini 3 and been impressed, but Anthropic has the killer app with Claude Code. The interplay of sonnet (a decent model) and the tools and workflow they’ve got with Claude code around it supercharge the outcome. I tried Gemini cli for about 5 seconds and was so frustrated, it’s so stupid at navigation in the codebase it takes 10x as long to do anything or I have to guide it there. I have to supervise it rather than doing something important while Claude works in the background
Re: Gemini CLI tips and tricks for agentic coding
#79I really wish there were a de facto state-of-the-art coding agent that is LLM-agnostic, so that LLM providers wouldn't bother reinventing their own wheels like Codex and Gemini-CLI. They should be pluggable providers, not independent programs. In this way, the CLI would focus on refining the agentic logic and would grow faster than ever before. Currently Claude Code is the best, but I don't think Anthropic would pivo…
> I really wish there were a de facto state-of-the-art coding agent that is LLM-agnostic
Cursor?
It’s really quite good.
Ironically it has its own LLM now, https://cursor.com/blog/composer, so it’s sort of going the other way.
Re: Gemini CLI tips and tricks for agentic coding
#80I really wish there were a de facto state-of-the-art coding agent that is LLM-agnostic, so that LLM providers wouldn't bother reinventing their own wheels like Codex and Gemini-CLI. They should be pluggable providers, not independent programs. In this way, the CLI would focus on refining the agentic logic and would grow faster than ever before. Currently Claude Code is the best, but I don't think Anthropic would pivo…
Goose?