If anything, the latest generation of AI models, Astra and Fable, are prime example of overfitting—whereas benchmarks suggest they’re AGI-tier, users (including myself) report the same old gaslighting, hallucination, context rot, cheating, incomprehensibility patterns as with prior models, sometimes even more pronounced.
Fable and Opus 5, I suspect, will become textbook examples of RL collapse.
Fable and Opus 5, I suspect, will become textbook examples of RL collapse.