InGoPenAIbyMichael Humor·Feb 26, 2025Running DeepSeek at Home on Mac with a Remote Web UIinstall ollama and deepseek
InGoPenAIbyMichael Humor·Dec 12, 2024What does the command “rm -rf /” do and what if an AI produces it?Key Takeaway:
InGoPenAIbyMichael Humor·Nov 6, 2024A Note on LLM Prompt Injection AttacksPrompt injection is a fundamental threat to LLM applications. Essentially, LLMs cannot reliably distinguish instruction (i.e., commands…
InGoPenAIbyMichael Humor·Sep 28, 2024How to deploy Pixtral 12B vision model on your own computer?Pixtral 12B is among the best (open-weights) publicly available vision models as of September 2024. In some use cases, it seems to even…
InGoPenAIbyMichael Humor·Sep 1, 2024How to use SGLang without GPU?SGLang is becoming a popular programming framework for LLMs. It has two main features: a front-end language and a backend runtime.
InDev GeniusbyMichael Humor·Aug 26, 2024How to create a large number of new users on my Linux server?Imagine you are teaching a large class of students, and you have a programming assignment for the class to do on a Linux server.A response icon1A response icon1
InDev GeniusbyMichael Humor·Aug 26, 2024How to share a folder with users on my Linux server?Copy the folder to a place you want to share (e.g., /shared_folder):
InDev GeniusbyMichael Humor·Aug 26, 2024How to find all users on my Linux server?Run the following command to list all the human users (excluding system users):
InGoPenAIbyMichael Humor·Aug 7, 2024Llama 3.1 vs Llama 3 DifferencesIt seems Llama 3.1 outperforms Llama 3 significantly in terms of math and reasoning capabilities. For instance, according to the Meta’s…
InGoPenAIbyMichael Humor·Apr 26, 2024What LLM quantization works best for you? Q4_K_S or Q4_K_MIf you are working with a giant LLM, quantization is your friend to optimize performance and speed. There are so many different…A response icon1A response icon1