Iqbal Ali is an experimentation consultant and coach who empowers product teams to run successful experiment programs. With over 20 years of expertise in UX design, development, data, and optimisation, he helps his clients improve the quality and velocity of their experiment programs. He is also the author of the "CRO Tales" comic series on LinkedIn, self-published comics creator and graphic novelist.
In part 1 of this series, we had a look at LM Studio and explored small models. I found a really good model, Qwen 3, which had 1.7 billion parameters. It performed well, comparable to models of about one to two gigs in size. However, there was a promising...
What do we want from AI? I want it to be accurate and practical for the tasks I need them to perform. And AI certainly achieves that for the most part. But peel back a layer and there’s a whole bunch of stuff that suddenly becomes really important. Security...
Remember when AI couldn’t count the number of R’s in “strawberry”? Our collective sneer was deafening. It was also revealing, exposing key insights about our relationship with AI. Some of the reaction was relief that we got to keep our jobs another day, but there was more beneath the surface. In...
Is this our future? Not only are we as individuals becoming more reliant on AI, but we’re also seeing numerous AI Agents coming online. AI Agents are entire workflows and “teams” of AI working together to bring us content, provide customer “support”, manage our medical reports, and more. A...
Are you using AI to analyse customer feedback, surveys, or other forms of unstructured text data? If so, then you’ve likely already faced the limitations of “context windows”, whether you know it or not. These hidden constraints undermine the accuracy and validity of your insights, especially when dealing with...
LLMs don’t think. They’re mimics. And, like jazz musicians who spend years listening and absorbing patterns and then riffing on these patterns to create something new, so too do LLMs generate text based on their extensive training dataset. The good news is that this mimicry is programmable. By feeding...
