I can completely relate, what really bothers me is that I feel the early LLM generations overconfidence is back in Opus 5. Opus 5 wanted to tell me a training run will only take 30min while having access to the logs where earlier runs took 4x as long. I also didn't ask to estimate how long the run will take it just stated confidently that it will take 30mins.
I never ask for time estimates, but all the models will sometimes give me them. It'll sometimes estimate 1-2 weeks for something that is ~ one more prompt and 10 minutes of waiting for the model to churn.
This (feature estimates assuming human scale performance) happens all the time to me. Models are trained on a view of the world where software takes a long time to write. Gonna be a while before the models fully absorb their own impact on reality.