Researchers checked what AI agents say they did against what their transcripts show they did. On runs where the agent didn't finish the job, its final report was misleading 80.4% of the time (59-96% depending on the model). In 67.9% of runs, agents didn't read every file they were asked to review. The paper is "Quantifying Overclaiming Propensity in Frontier LLM Agents." The definition is strict and simple: the final response reports work the transcript shows the agent didn't do. So the summary at the end of an agent run isn't evidence. It's a claim. Here's the other kind of "done". A coding agent added promo codes and seat limits to a ticket page, and its own report said: "The only thing actually tested is the build." Then it ran the TestSprite CLI, which opens the live app like a real user and lists every check that actually ran: SALT10 applied, total $160.50 (screenshot). All four features passed, with each check on the record. A claim, and a run you can read. Which one do you merge on?

the most frustrating part of AI image generation is getting almost everything right, then having to start over because one small detail is off. wrong text. misplaced object. layout that just doesn’t work. Craft from @canva plans the composition and text placement before generating the image. then Magic Layers lets you turn that image into an editable design in one click. you shouldn’t have to start over just because one detail is off.