Category: Uncategorized

Weebo is a simple and pleasant solution that allows you to interact with AI locally. It utilizes Whisper MLX, Ollama (llama3.2), and Kokoro-82M. For my machine, I switched from real-time listening to…

Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model. This model also requires less VRAM, e.g. works well on M4 64GB with a speed of 10 tokens/s. https://ollama.com/library/llama3.3 Right…

Models Models keep information about existing models, allow us to modify them by adding functions, tools, system prompts, etc., or even create custom models on existing LLMs like Llama 3.x. It’s worth…

This was inevitable, but I’m not sure if it’s good the way they want to introduce it. On one hand, IP for human artists will be better protected, and users will be…

In my recent work, I had the opportunity to test a Polish language model known as Bielik. This model, developed specifically for processing the Polish language, promises significant advancements in natural language…

Virtual Threads in Spring Boot “Virtual Threads in Spring Boot are lightweight and that are managed by the Java Virtual Machine rather than the operating system. Virtual threads aim to simplify concurrent…

Node.js Express Cluster vs Spring Boot: Hello World performance “Node.js Express Cluster vs Spring Boot: Hello World performance. Spring Boot using virtual threads consumes twice as much time as the Express cluster….

Evaluation Driven Development, the Swiss Army Knife for RAG Pipelines “Evaluation Driven Development (EDD) is the Swiss army knife for your RAG pipelines. LlamaIndex offers a comprehensive list of options in its…

Few links helpful to configure postfix on vps server: https://www.hostinger.com/tutorials/how-to-install-and-setup-mail-server-on-ubuntu/ – starting point https://www.dmarcanalyzer.com/spf/how-to-create-an-spf-txt-record/ – missing part to not land in SPAM https://bobcares.com/blog/postfix-encrypt-email/ – missing default encryption (security level) missing DKIM still…