"Engineering" (9 posts)
OpenAI ChatKit Review: Technical Deep Dive and Why We Didn’t Adopt It
We evaluated OpenAI ChatKit and chose not to adopt due to architectural mismatch, limits around human handoff, and constraints on deep white-label customization.
Did I get a little bit hacked by ChatGPT here?
Generative AI gives a new flavour to Cross-Site scripting attacks
Challenges of building an AI Agent on top of Shopify MCP
Shopify MCP looks like a plug-and-play solution, but building an AI Agent that performs reliably on top of it involves surprising complexity.
How Model Context Protocol works. MCP Explained
Still unsure what MCP actually does? Let's clear it up, one step at a time.
What makes an LLM generative? AI copyright law and the Schrödinger's cat
Do Large Language Models create original text or just perform high-tech copy-paste? Lawyers may have to settle that debate before technologists and philosophers even get the chance.
We tested DeepSeek. Here's what you need to know
Some say DeepSeek R1 is a game-changer, others say it's impractical. Both are right.
LLM benchmarks: What are they and can you trust them?
Explore the world of LLM benchmarks, understand how models are evaluated, and learn why benchmark results should be viewed critically in the competitive AI landscape.
RAG vs Fine-tuning for your business? Here's what you need to know
Considering custom AI solutions for your business? Discover how Retrieval Augmented Generation (RAG) offers a flexible and affordable alternative to fine-tuning LLMs.
GPT Tokens Explained - what they are and how they work
Large language models generate text token by token. But what are tokens exactly? And how do they relate to entropy and data compression?