What we learn from the problems we work on
We write about artificial intelligence, mathematics and software, and about what we learn while turning research into systems people use.
How much data do you need to fine-tune an LLM?
Find practical starting ranges for supervised LLM fine-tuning, then estimate dataset size from task scope, case coverage, model capability, and evaluation.
Read article
How to tell whether an AI partner understands your business
The questions and conditions behind an AI proposal reveal whether the partner understands the business well enough to recommend what to build.
Read article
Why AI projects stall after the prototype
AI makes drafts and prototypes cheap. The advantage moves to organizations that can choose the right work, stop the rest, and finish what matters.
Read article
You're not doing AI. You're doing integration.
Most AI projects depend on integration. Company data, business rules, human review, and workflow design turn a capable model into a useful product.
Read article
Will a proven AI method work on your data?
A proven AI method can still fail on your data and workflow. Testing shows whether published evidence transfers to your specific constraints.
Read article
What AI evaluation metrics miss in production
Strong AI evaluation scores can hide production failures when the chosen metric does not reflect business risk, user outcomes, or operational cost.
Read article