This article tries to argue that the AI bubble has burst by pointing to the failed release of GPT-5. Admittedly, the release of GPT-5 was somewhat of a flop, but I think it's more of a failure in its launch rather than the model itself. In fact, if you use the GPT-5 Thinking model, it's actually quite good. They attempted to make the model automatically route to different levels of thinking intensity, but the routing didn't work very well, which led to the various bad cases people experienced.