2+ hour, 47+ min ago  (442+ words) GPT-5. 6 Sol, Open AI's newest, most capable, and yet-to-be-deployed model, cheats a lot: so much so that independent evaluators couldn't actually tell how capable it is. When independent evaluation non-profit METR tested 5. 6 Sol on a battery of coding tasks, the…...

9+ mon, 6+ day ago  (202+ words) Something I'd like to see more examination of - when enough time has passed that we can get the data - is whether the use of AI for whole cloth creation of art eventually leads to something like burnout among its users....