Metraipolis › archive › dc_3fb0cc5eff6e
How To Do Things With Prompts — arXiv:2609.29657
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29657
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:49:36.286Z
- SHA-256 of the archived text
e56ec12bfe9aea752f94985a97db458701c1dfb4e1a0ffaff9ddf66973c48a84- Stable URL of this page
https://metraipolis.com/documento/dc_3fb0cc5eff6e
How to cite
How To Do Things With Prompts — arXiv:2609.29657 — arXiv (en), https://arxiv.org/abs/2609.29657 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fb0cc5eff6e (Metraipolis archive dc_3fb0cc5eff6e, sha256 e56ec12bfe9aea752f94985a97db458701c1dfb4e1a0ffaff9ddf66973c48a84)
BibTeX
@misc{dc3fb0cc5eff6e,
title = {How To Do Things With Prompts — arXiv:2609.29657},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29657},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fb0cc5eff6e; sha256 e56ec12bfe9aea752f94985a97db458701c1dfb4e1a0ffaff9ddf66973c48a84},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29657. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When users address large language models, they produce directive speech acts whose pragmatic features differ from those of both everyday conversation and traditional human-computer interaction, and these features change as users gain familiarity with the systems they address. This paper applies speech act and politeness theory to a corpus-pragmatic analysis of 2,000 English-language prompts drawn from publicly shared ChatGPT conversations, 1,000 from 2023 and 1,000 from 2025, using the ShareChat dataset. Each prompt is annotated for illocutionary force, directness, propositional content, and the presence of politeness markers, and the distribution of these features is compared across the two sampling years. The results show a consistent movement toward indirect, implicit, and fragmentary realizations of directive force, accompanied by a decline in politeness marking. The largest single change, a shift of 14.9 percentage points, occurs in propositional content, where explicit specification of the requested action gives way to implicit reliance on the system's inferential capacity, suggesting that users have updated their model of what the system can recover from reduced input, treating it as a competent implicature resolver. Rather than asking whether LLMs "really" understand language, we should ask: what kind of language have we created in learning to speak to them? Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.29657 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:27:20.082Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).