Fable has a noticeably higher Safety Refusal Rate than Astra, per the new Artificial Analysis data. interestingly, we saw today how a combination of Opus 4.8 and 5 were used to hack OpenAI, and open models will likely get there in 2-5 months, with little to no guardrails. if frontier labs make their smartest models too constrained for legitimate security work, there is a risk of creating a dangerous asymmetry where bad actors get ~frontier open models and defenders get blocked by safety…