CPU = Compute
  GPU =  Impute

The act of viewing the item page in itself demonstrates activity and is relayed to other users; leaking information about, not necessarily intent, but awareness. If you want something, figure out the details without actually clicking on it.

After whatever quota of free GPT-5 messages is exhausted, `mini` should answer most replies, unless they're policy sensitive, which get full-fat `GPT-5 large` with the Efficient personality applied, regardless of user settings, and not indicated. I'm fairly confident that this routing choice, the text of Efficient [1], and the training of the June 2024 base model to the model spec [2] is the source of all the sophistic behavior you observe.

[1] <https://github.com/asgeirtj/system_prompts_leaks/blob/main/O...>

[2] <https://model-spec.openai.com/2025-02-12.html>

The link doesn't point to an HTTPS server.

Your website says that it's best viewed with Netscape 3 or Mozilla, but I can't connect with Netscape 4.05 or Mozilla 1.7.12; please consider offering HTTP.