What's the difference between a Tool, a Chatbot and an AI Agent? A practical guide to understanding these terms and when to use each, with a real-world example of how to redesign a broken process.
Continue reading
Training produces a capable but rough model. Making it useful requires evaluation, fine-tuning, and serious optimization. A look at the post-training work behind BLOOM, and an honest verdict on how it performed at launch.
Continue reading
A step-by-step walkthrough of how BLOOM's 176 billion parameter architecture actually processes language, from token embeddings through 70 decoder blocks to the final output prediction.
Continue reading
Over 2 million models are now hosted on HuggingFace, with the second million added in just 335 days. If open source models are viable alternatives to OpenAI and Anthropic, how do you justify those companies' valuations? A deep dive into BLOOM, the only truly open source LLM.
Continue reading
A brilliant explanation of what's actually happening inside modern AI systems, and what remains mysterious and unresolved.
Continue reading
Most dashboards treat KPIs like a scoreboard. Green equals good, red equals bad. Useful for reporting, but terrible for decision-making. A KPI Driver Tree flips this idea around.
Continue reading
When personalised tools can be created in days, broad vanilla platforms start to feel useless. I built my own AI job tracker in a day and a half.
Continue reading
Ethan Mollick's Co-Intelligence offers a clear, accessible introduction to using large language models as collaborators. It's the perfect on-ramp for AI newcomers, though seasoned users may find familiar ground.
Continue reading
Each time a machine crosses a new threshold, many people insist: that doesn't really count as intelligence. Why do we resist calling machine behavior intelligent?
Continue reading
Fluency doesn't come from studying language. It comes from generating it. That's why I built Babblo.
Continue reading
Jeff Hawkins' 2005 exploration of intelligence as prediction was ahead of its time in some ways, but missed the mark on others.
Continue reading
Karen Hao's Empire of AI attempts to capture the OpenAI story while it's still being written. The result is part insightful journalism, part premature verdict.
Continue reading