JayByte

A track of the ending 2025 year:

I developed my first pet-project in 2017. It's an arcade Unity game with custom level maps, logic of collecting items etc (

File folder on MEGA

). In the previous year I made interactive YTPs and I was more into crafting videos and animations. However I started my web dev career in 2019. It's interesting to see how hobbies can predate the next epoch. #blog #life #slowlife #softwareengineer #programming

I love this slice of Software Engineering cake! #softwareengineering #softwaredevelopment #programming #blog #thoughts #meme #memes

Many people may ask something like: "how does cooking relate to programming which is your career and passion? how does your philosophical speech relate to it either?". Actually side hobbies help me in developing programming skills, when current abstract understanding hits a wall. For example, cooking activated more clarity for multitasking/parallel programming in me. Idk how this works. Brain is wonderful. And philosophical posts are a form of reflection and leisure. And reflection is essential to understand software development at different levels: from coding to architecture to business. Not everything is effectively implemented solely at code or architecture level tho. #blog #thoughts #programming #softwaredevelopment #softwareengineering #hobbies #leisure

You can install the latest release of PromptQL from here: gitlab.com/jbyte777/prompt-ql/-/tree/release-6.x #promptql #prompts #promptengineering #llm #distributedprompts #programming #library #opensource #golang #go

Do you remember when on the onset of AI hype many "AI experts" told that coding UI would be a first thing from programming, which LLMs would automate? #llm #coding #ui #ai

1-2 years ago I was working on an artistic pet-project which aimed to be catalogue of various pharmacy products. This was kinda mixed art with unique design, easter eggs and custom perfomance-oriented back-end. I developed various utilities and services during development of the project. You can read about them in my Medium: https://medium.com/@jzx777 #programming #craftprogramming #art #frontend #backend #web

1. Work should be ecologic for humans as creative and explorative beings which live as long as they essentially can. 2. So the best code which solves a given (real or imaginary/perspective) problem, is no written code. If this solution for given problem exists. 3. Periodicity of multiple patterns/modes is a mitigation of negative effects of the Goodhart’s law. “Work hard” and “follow easy path” are also patterns with limits. 4. So write less boilerplate “monkey” code, write more business-related and engineering code which provides you a solid basis for future development without energy draining mundane work. #blog #programming #softwareengineering #work

4 months ago I wrote another article on making bots by prompt engineering with PromptQL. I explained how expansion and execution of code embeddings brings full power to prompt templates. Here it is: https://medium.com/@jzx777/making-bots-with-promptql-code-embeddings-5b21efd52c51 For purpose of examples, I ran bot with the Openhermes Mistral 2.5B model and the llama.cpp server. Openhermes model:

TheBloke/OpenHermes-2.5-Mistral-7B-GGUF · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

llama.cpp server: https://github.com/ggerganov/llama.cpp/tree/master/examples/server #PromptQL #promptengineering #prompts #ai #golang #go #programming #opensource #library #programminglanguage #llm #LocalLLM #openhermes #llamacpp #cottagesoftware #craftprogramming #indietech

4 months ago I tested my audio stories generator on the Nous Hermes 10.7B model which runs locally on my CPU. And on llama.cpp server. And there are results! The stories generator (built with PromptQL front-end and Nous Hermes, OpenAI TTS back-ends) is here:

GitLab

Files · with-nous-hermes-10.7b · JByte / storybox-generator · GitLab

GitLab.com

The Nous Hermes 10.7B model can be downloaded here:

TheBloke/Nous-Hermes-2-SOLAR-10.7B-GGUF · Hugging Face

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

The llama.cpp server can be installed from here: https://github.com/ggerganov/llama.cpp/tree/master/examples/server #PromptQL #texttospeech #llm #locallm #promptengineering #prompts #messageprotocol #agents #golang #go #programming #opensource #library #indietech #programming #ai #generativeai #blog