Theo Browne reviews the Fable 5.2 release and its reported benchmark results, including coding and scientific tasks. He contrasts those figures with his own evaluationsEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria., where the model sometimes made incorrect claims about codebases.
Theo Browne examines subscription limits and estimates usage under his testing conditions. He describes model speed and pricing changes and labels his ideas about their underlying causes as speculation.
Theo Browne compares generated interfaces, debugging assistance and game prototypes. He reports strong technical performance alongside mistakes requiring human reviewCode review examines proposed source changes to assess their correctness, clarity and suitability before or around integration., and says different models performed better on different parts of his work.
Watch on YouTube




