... also, instead of just using all this stuff out there, like all the OpenClaw stuff, memory systems, what I am doing so that I understand it is just create my own from scratch I have not even read about how that one works, I spin up 10x copilot -p "idea", in the new automate mode they just added, in Docker container, 5x gemini cli in pro 3.1 then 5x flash 3.1, gpt 5.4 in there somewhere along with 5.3 codex, o3, 04-mini (crappy agentic models, BUT, that is okay because often that means they have some more intelligence that the more agentic models lack) scan those with my brain then run all the passing ones into a Best Of N scenario to compile a best/better etc. I have a whole system that works well - certain things will cause all these models to respond differntly, while other things will get them to mostly respond the same - which means something useful.

With all of the talk about "LLMs are non deterministic" I am trying to build my own tool (at this exact moment, since I seem to have gotten really good at this) which does some of what these OpenClaw/Clawdbots do for people, but instead of having these LLMs/agents handle everything I am trying to do as much of it as pure deterministic code as possible. I test things once, like daily automations, and they will repeat that way the next scheduled date/time. Also, anytime AI models are used, at first I am approving/analyzing a docker/podman/microVM container to make sure it is only EXACTLY what it needs for a job, and then that is saved for future. I approve it once, and then it is there for future use.

Also I happen to know a few useful things, from a year + of working with all of these models, tools, daily for usually at least 8..12... 15 hours a day (I cannot stop, I love it, and I am good at it). I just noticed someone finally posted what I figured out a year ago - when you do need the help of a LLM, and you need it/want it to be as safe and as deterministic as it can be - Use the biggest, best, smartest models for the "brains" but for ALL the agentic stuff, the tool use, the MCP servers, etc, use a smaller model. Current best models for that - MinimaxM2.5, Gemini 3.1 Flash (use pro for planning, fixing, problem solving, all the difficult stuff, but definitely use the smaller Flash for the agentic tool use) Its weird that I have known this for so long and it has barely caught on yet.. I did have some AI guides that went viral on HN months back wuu73. org/aiguide or /aicp (free tool, well loved) I should write more about all this stuff i've figured out so I am not dumping paragraphs on so many posts over and over like this.. if my tool ends up useful I put it on my site somewhere in the AI tools sections if you want to put your email in the RSS thing, I will try to put anything useful on there/update RSS

So do you have a tool to suggest?

Just wanted to share that this actually does work with Claude Code, and I can use Github Copilot's Opus models in CC without burning up all of the premium requests.. they figured out how to fix that. Copilot is a great deal for how much you get for $10

Right now Google Antigravity has free Claude Opus 4.5, with pretty decent allowances.

I also use Github Copilot which is just $10/mo. I have to use the official copilot though, if I try to 'hack it' to work in Claude Code it burns thru all the credits too fast.

I am having a LOT of great luck using Minimax M2 in Claude Code, its very cheap, and it works so good.. its close to Sonnet in Claude Code. I use this tool called cc-switch to swap out different models for Claude Code.

Lately, I’ve been using Claude Code skills/plugins.

One is called Superpowers (you should be able to find it by typing “claude code superpowers github”), and there are many other skills installed for all sorts of things. Gotta give props to whoever came up with the skills idea at Anthropic. It’s a smart way of handling context — instead of dumping pages of helper text into the prompt (for example, how to properly build a frontend website), it just provides some metadata and lets the agent decide whether it needs to load more.

I highly recommend spending time finding and installing lots of these skill plugins. They can make even the cheapest small AI models work way better.

I’ve been using the Superpowers plan mode: it creates a detailed plan first, then there’s an execute mode (and a few others I’m forgetting). I can give it a long, hard task — like converting a large app to another language - and if I run plan first and then execute, I can just let it run for hours and come back to something that’s basically done: fully tested, following best practices, with most bugs fixed.

There are some skills for frontend development, and now anytime I make a website, its crazy amazing looking and has all the stuff I usually forget.

I made this for my sister who has been curious about AI and coding (she is not a programmer). Its because I didn't want to sit and download each program individually, install each extension, Git, Node, ... also random people at work, lots of people get curious after me telling them how much fun it is.

I could not find any similar thing out there..

Includes at least two totally free and excellent free tier's of AI coding tools/APIs that can be used in the installed VS Code (auto-installs a couple AI coding extensions). Includes links to some other information I wrote about how to keep costs low or zero.. specifically for AI to help code (something that was trending on HN last month).

Its useful for when you are having random conversations about the topic and people are curious and want to maybe experiment... but have no idea how to start or what to do. Some people will loose interest when there are tons of steps or friction.

I could improve this a lot if anyone actually ends up using it besides myself, better docs and maybe a guide or example(s) step by step how to make/code something cool (or, links to some guides, videos, blogs/sites - I enjoy getting people into cool stuff like programming! If you can show someone how much cool things they can do before the brain boredom hits, they'll get some dopamine and maybe come back to it.

Interested in any feedback negative or positive, i'm probably missing a few things that should be included... I don't want to ever add anything spammy/scammy, things that you spend time to learn then they manipulate you into paying, no evil things etc.. no "gotchas" marketing "trickery" If I were to remake it i'd do it different: web/JS version where the checkboxes are online, and it creates a more custom script. More options and operating systems but with 2 or 3 good simple defaults to pick from.

The free AI models are Qwen3 Coder, Gemini 2.5 (probably 3 soon) Pro.. and there are usually one or two more that are built into the VS Code extensions Cline, Kilo Code. GLM 4.6 is $9 for 3 months. Github Copilot is an excellent value for all the Claude 4.5 credits they give you for $10 (maybe its temporary but I can go with the agent for hours, barely using 2%!)

--- Some people hate the phrase "vibe coding" but my own mother asked me if I had heard of it. Its out there in the consciousness and scammers are also out there in the same spaces, waiting in the bushes.. ready to pounce on people who don't know there are simpler, cheaper ways to access & use AI

I think it is my favorite model out of all of them. Its the one I tend to go to for just about everything now. I just found something called Octofriend that is supposedly really good set to GLM 4.5.

I have used it, but I just haven't found it good when I have, maybe its gotten better.

I have it as one of the free models in a chrome extension I was working on since I keep a list of tons of free APIs, just there are so many options and I tend to just use the top 5-10 best ones (that I have noticed as being great)

There has got to be probably 100 of these tools by now, yours is the only other one that has a UI that I have found.

Lot of people all get the same idea eventually.. we all run into the same problems eventually

What are you using GPT 4.1 with, anything? I find that it will follow your instructions REALLY well, so maybe whatever you are using it in, there is a problem with the prompt. Something might be telling it to do that. It really does do whatever you tell it (but you might not be able to see the full prompt if you are using GPT 4.1 with some kind of other tool/not raw).

Using it in Cline (free VS Code extension) it does exactly what it is told to do, I will have a bigger/smarter model figure out plans for it. It will edit files and just do stuff but its not really the model to think or plan etc.