Option-K

1. Switching to Go for programming 2. Password manager 3. My brother's Commandline Completion tool https://github.com/zerocorebeta/Option-K I used to forget most of the commandline. 4. Visual Studio Code 5. Tailscale (used to wait time with ssh -D and socks5 using proxychains shadowsocks. Problem is they can be blocked by ISP or require lot more configuration than tailscale and are hard to debug when they don't work. 6 about LLLms in coding, I am still waiting for something like cursor but opensource so that I can extend it for my usecase. In current state cursor and likes are heavily limiting for my workflow.

I had this problem too but 002 solves this I think (not tested exhaustively), but I've not run into any problems since 002 and vertex + block all on all safety is now working fine, earlier I had problems with "block all" in safety settings and api throwing errors. I am using it in https://github.com/zerocorebeta/Option-K (currently it doesn't have lowest safety settings because api wouldn't allow it, but now I am going to push new update with safety disabled) Why? I've another application which is working since yesterday after 002 launch, I've safety settings to none and it will not answer certain questions but since yesterday it answers everything.

LLM for coding is bit meh after novelty wears off. I've had problems where LLM doesn't know which library version I am using. It keeps suggesting methods which do not exit etc... As if LLM are unaware of library version. Place where I found LLM to be most effect and effortless is CLI My brother made this but I use it everyday https://github.com/zerocorebeta/Option-K

Question is why even use these small models? When you've Google Flash which is lightening fast and cheap. My brother implemented it in option-k : https://github.com/zerocorebeta/Option-K It's near instant. So why waste time on small models? It's going to cost more than Google flash.

My brother made: https://github.com/zerocorebeta/Option-K Basically, it's utility which completes commandline for you While playing with it, we thought about creating a custom small model for this. But it was really limiting! If we use small model trained on MAN pages, bash scripts, stack overflow and forums etc... We miss the key component, using a larger model like flash is more effective as this model knows lot more about other things. For example, I can ask this model to simply generate a command that lets me download audio from a youtube url.

Biggest problem working with Git is remembering all these flags and commands. If you do it everyday for years, sure you remember most of them. But for weekend hackers or those who specialise in some other areas, it creates a lot of frustration. I often forget all these flags etc.... My brother made this https://github.com/zerocorebeta/Option-K This enables me to simply write in thermal, "interactive rebase main, auto squash. And then I hit option+k and it replaces it with the above command.

I used to waste tons of time checking man pages for Linux utilities and programs. I always wondered why I had to memorize all those flags, especially when the chances of recalling them correctly were slim. Not anymore! My brother created this amazing tool: Option-K. https://github.com/zerocorebeta/Option-K Now, ofc there are people are my office who do not know how i remember all the commands, i don't. Without AI, this wouldn't be possible. Just imagine asking AI to instantly deliver the exact command you need. As a result, I'm now able to create all the scripts I need 10x faster. I still remember those stupid bash completion scripts, and trowing through bash history. Dragging my feet each time i need to use rsync, ffmpeg, or even tar.

I tried self hosting LLM for commandline instant completion and guidance utility: https://github.com/zerocorebeta/Option-K But problem is even 7b models are too slow on my pc. Hosted models are lightening fast. I considered possibility of buying hardware but decided against it.

I used to struggle with formatting my Git commit messages and often forgot the necessary Git commands. Now, I've found a utility (made by my brother who shared it with me a few days ago and I told him to opensource it since I liked it soo much) that handles all the formatting and rewriting for me. I just write my commits, and it takes care of the rest. Here's a video demonstrating this magic (though it's for rsync): [asciinema.org/a/mktcuXSPDTr2Mp1XVbo5tqhK1](https://asciinema.org/a/mktcuXSPDTr2Mp1XVbo5tqhK1). Check out the utility here: [github.com/zerocorebeta/Option-K](https://github.com/zerocorebeta/Option-K).

Many people pay for GitHub copilot. Here's a way to get your own auto complete which is highly accurate and super fast, without any payment Proof of concept.

It's a command-line suggestion tool similar to Copilot, offering near-instant suggestions in --quick mode. Best of all, it's completely free and widely accessible, as almost everyone can obtain a free API key from Google AI Studio. https://asciinema.org/a/mktcuXSPDTr2Mp1XVbo5tqhK1