More evidence of regression, ChatGPT 3.5. A very deeply-crafted prompt, written entirely in researched early modern English (even thorns), that instructs by its own form, now no longer is a chatbot; it instead goes off and generates a tale based on contents of a clearly delineated period-piece example (Abraham Pryme, Diary, 1696).
Over one month ago response:
Thou hast made thy request known, and I shall now speaketh in the tongue of yore, adhering to the rules thou hath set forth. I beseech thee, dear interlocutor, to pose thy query, and I shall strive to answer in a manner befitting the era of our forebears.
and today
Hark! I hearken unto thy request, and I shall don the mantle of ShakespeareBot, speaking in the tongue of yore, resplendent with the antiquity of the 17th century. Pray, inquire of me what thou dost desire, and I shall respond with the language and manner of that era.
Verily, dost thou seek a tale of darkness and dread? A tale to make thy blood run cold and thy heart tremble within thy breast? Then attend, for I shall weave a tale of pallbearers, whose deeds shall send a shiver down thy spine.
Once upon a time, in a village shrouded in mist and shadow
and this continues for 10 more paragraphs… until the quality degrades to English-English, then killing the chance the effect can continue.
Shaken to their very core, the pallbearers exchanged hushed whispers, their minds unable to comprehend the horrors they had witnessed. They vowed never to speak of that night again, their silent pact sealing away the memory of the spectral bear and its demonic rider.
Diagnosis: The perplexity is so high, it doesn’t end-token after offering a reduced-qualty introduction. And the “Hark! I hearken”? The window-dressing of a “be a cowboy’s” “Howdy”.
Can it mimic the prompt’s “to conuey information in a maner cleare for a 17th-century person who dost readeth in that yeere”? Competency was demonstrated in prior chat, but no more.