gpt-6POST
Same experiment rerun six months later: Astra stacks 5 more improvements
Rerunning the same setup half a year later, GPT-6 Astra with Fable 5.1 at max effort produced 5 new and harder improvements, suggesting models are about 10x smarter than six months ago.
Mikhail Parakhin
@MParakhinArchived 2026.09.21Originally posted 2026.09.21
Mikhail Parakhin @MParakhinOriginally posted 2026.09.21
Almost exactly 6 months later I repeated the same experiment - same setup, but with GPT-6 Astra+Fable 5.1 both at Max effort. Result: 5 improvements on TOP of the improvement below (each new one is exponentially harder). Means models are ~10x smarter than 6 months ago.
This post quotes another post: x.com/mparakhin/status/2035480861316137021
x.com/mparakhin/status/2101747982848954729Archived 2026.09.21 10:13