Leaving model effort at maximum for every task means avoiding a decision I still own. The Opus 4.8 announcement on May 28, 2026 put effort controls front and center. I like having the control. Dragging a selector all the way to the right, though, tells me very little about whether I have assigned the right amount of work.
Model selection should follow the task: use what makes sense for the job. I expect the same of effort. How much the model investigates needs a reason too.
A wording change with a settled request deserves an edit and a check. A change across several parts of a codebase can need investigation first. Giving both the same setting skips the decision and costs more, including my time waiting while an agent develops another plan for something that was already decided.
Extra effort needs to buy something I can identify. Finding a hidden dependency is worth waiting for. Restating the uncertainty in four paragraphs does little for delivery. The work returned to me also counts: if I have to explain the request again or reconstruct what happened, that quick response cost more than it looked.
For a comparison, I want a bounded task and a definition of completion written before the answer arrives. Then I look at what changed with the setting: whether review got easier, whether the agent caught something that would otherwise have slipped through, and whether it resolved the uncertainty that justified investigating. With that, I can defend the setting I pick.
I also want the setting to follow changes in the task. A small edit can expose a serious constraint, and an investigation can finish sooner than expected. Thinking after the uncertainty is resolved just delays execution. A brief update about the remaining question is enough; I do not need a transcript of the reasoning dumped into the conversation.
In the next comparison, high effort stays as the default only if it shows a concrete benefit. I will separate clear tasks from investigative ones and judge the delivery alongside the review left for me.