AI-ML
2025
AI Capex between 2022-2025
·506 words·3 mins
Lets explore the data of the AI infrastructure investments from NVIDIA, AMD, and hyperscalers like GCP, AWS, and Azure.
AI milestones in 2025
·111 words·1 min
2025 brought us Claude 4, MCP, Agents, GPT-5, o3 reasoning. A timeline of artificial intelligence developments, breakthroughs, and milestones throughout 2025
OpenAI Shows Someone Else's Conversations
·993 words·5 mins
I sent a picture to ChatGPT for OCR and it gave me a response that leaked from somewhere.
Switching from LMStudio to Ollama + OpenWebUI
·375 words·2 mins
Why I moved from LMStudio to Ollama and setting up OpenWebUI as frontend.
2024
AI milestones in 2024
·88 words·1 min
2024 brought us GPT-4o, Claude 3, Gemini Ultra. A timeline of artificial intelligence developments, breakthroughs, and milestones throughout 2024
Is an AI agent a sophisticated version of a loop ?
·637 words·3 mins
Looking at the current state of agents, It is possible to replicate them with a simple loop.
Ollama Environment Configuration
·66 words·1 min
Key environment settings for running Ollama efficiently on Windows and Linux.
Force Ollama to use only a single Nvidia GPU
·163 words·1 min
Selecting and enabling which GPUs are visible to ollama within windows.
Base Mac Mini M4, The alternatives for Low-End NVIDIA Hardware for Inference
·741 words·4 mins
How the Mac Mini M4 has enabled affordable Local LLM inference and making VRAM-starved NVIDIA cards obsolete for low power and low cost
The Strawberry Challenge, When LLMs Need Tools to Count
·170 words·1 min
Around October 2024, The infamous “How many R’s are in strawberry?” question has become a fascinating litmus test for Large Language Models, exposing a fundamental limitation in how these systems process text.