Managing the full YouTube content lifecycle — from idea to publishing — is repetitive and time-consuming. To address this, I built an automated pipeline that...
Read MoreBlog
What Are RAG and KAG? When to Use Which
Artificial intelligence has brought us new ways to connect large language models with external knowledge. One popular approach is Retrieval Augmented Generation, or RAG. Another...
Read MoreWhat is Context Coherence in RAG? Why Does It Matter?
I work with Retrieval Augmented Generation, or RAG, almost every day at GPT-Lab, Tampere University. It is a method where a system looks up information...
Read MoreLLM Radar: Catch the Latest AI Papers Before They Vanish into the Void
Generative AI moves like a runaway train. “I’ll catch up this weekend” is a lie we tell ourselves between experiments, code reviews, and reviewer 2....
Read MoreContext Engineering: How to Stop Your AI from Forgetting What Matters
The Story: When a Chatbot Forgets Your Shopping List It was Black Friday morning, and Alex was on his favorite electronics store’s website. He opened...
Read MoreGPT-5: Breakthrough or Just a Better Autocomplete?
Highlights Exhibits PhD-level intelligence, but still doesn’t self-learn once deployed Thinking Mode unlocks deeper chain-of-thought reasoning when prompted (“Think hard about this…”) Accuracy soars: 94.6...
Read More