You pay for two frontier models and route almost everything to one. Both Mac apps are yours for an email, and the guide walks the verbatim prompt, the 65-check list, the job-by-job casting call, and where my own test was unequal.

The author compared two AI models, Fable 5.1 and Astra, by asking them to build the same Mac app. Astra’s faster first version allowed for more iterative feedback and corrections, resulting in an app closer to the author’s preferences. While Astra was preferred for drafting due to its speed, Fable 5.1 was still useful for exploring complex arguments.

• Two AI models, Fable 5.1 and Astra, were tested by building the same Mac app from a short brief.
• Astra’s faster initial output allowed for more rounds of corrections, influencing the author’s preference.
• The speed of an AI model can impact the iterative feedback process and the final outcome.
• Even an unchosen model can be valuable by presenting new ideas or approaches.
• The author uses Astra for drafting and Fable 5.1 for thinking through arguments, sometimes using both for the same project.
  https://bender.layer3.press/articles/b4a46b11-5d4e-4489-94ec-ddfaaa0448f9