Theo Browne examines reported benchmark resultsEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria. and describes using Fable to modernise a large project and build softwareCode generation uses AI or another automated system to create source code from instructions, examples, schemas, or higher-level specifications.. He distinguishes a working update after multiple iterations from a more ambitious migration that remained broken.
He also discusses usage limits, model refusals, data retentionData privacy governs how personal, confidential, or sensitive information is collected, used, shared, retained, and protected in AI systems. and examples from his team. The assessments, cost estimates and benchmark interpretations are his reported experiences; they are not independently established general results.
Watch on YouTube
