I’ve written before about how November 2025 was an inflection point for coding agents—the point where Opus 4.5 and GPT-5.1 crossed a tipping point that meant their respective coding agents …
It’s actually insane what a majority of these people prompt for, especially with diffusion models. As if they completely neglect how these models are trained: images paired with text descriptions. Then writing instructions instead 😭
It’s actually insane what a majority of these people prompt for, especially with diffusion models. As if they completely neglect how these models are trained: images paired with text descriptions. Then writing instructions instead 😭