In a world where masses believe that LLMs are "everything boxes", some reality check is always good.

You say this, but the reaction I get from colleagues is increasingly "why bother training new models when you can just ask an LLM?"

Doesn't matter the domain or the task, the answer from some researchers is "LLM" always.

Yeah so that’s why we invented tool calls, and an LLM exercises judgment when it should simply place a tool call to do simple math.

Most people need to be reminded of this. Repeatedly.

This does make sense, however in view of the recent maths results and since there are tens of thousands of training images for skin cancer available on the public internet I was expecting the LLMs to perform a lot better than they did

And if you give the LLM a simple calculator MCP, then the calculator's outperformance disappears.