Skip to content

[ SIGNAL: LIVE ]

Emergent Minds

>>_

Posts

View all →

Marked Down for Being Right: Claude Fable 5.2 vs Opus 5.5 on Real Code

Claude Fable 5.2 costs twice as much per token as Opus 5.5. On 52 real tasks from a production monorepo, my tests scored it level or behind. Then I read the failures. Fable had fixed a bug the original human fix shipped with, and my tests marked it wrong. Plus: Anthropic's own system card shows the safety fallback hands attacked sessions to a weaker model.

READ

Two Hours of Carbon: Gemini 4 Carbon vs Argon on Real Code

Gemini 4 Carbon scored 17 clean runs of 20 on my production monorepo bench, one more than Argon and the best result so far. It took 30 minutes per fix, wrote more tokens than any model I have tested, and emptied a $99.99 Google AI Ultra quota in two hours. On December 1 the price doubles.

READ