Students reported that continued interaction with a cGPT improved its adherence to instructions¶
Claim · All claims
Evidence · 1 study · qualitativer?·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Students observed that the more a cGPT was used, the more consistently it appeared to adhere to instructions, leading them to view GPT development as ongoing dialogue rather than one-time configuration. → Lo S 2026
Evidence¶
Lo S 2026¶
Lo S, Lea T, Mavromoustakos A, Joseph B, Yii M, Exintaris B, Karunaratne N, Pearson DL, Ritchie T, Yuriev E and Pyun J (2026) Co-creating custom GPTs: an autoethnographic study of undergraduate students as partners in generative AI innovation. Front. Educ. 11:1818781. https://doi.org/10.3389/feduc.2026.1818781
q2 · i? · qualitative · r?
Inductive thematic analysis of summer-scholarship SPAR logs. Students anticipated outcomes of language choices better with continued engagement, reporting that "the more times the cGPT is used, the more consistently it may adhere to the instructions". The article presents this as a student interpretation, not a tested result.
"the more times the cGPT is used, the more consistently it may adhere to the instructions… ultimately resulting in a better custom GPT experience for users"
Discussion¶
Related Claims¶
- Students' evaluative judgment of cGPT responses shifted from strict principle compliance toward contextual appropriateness — related
- GPT responses reliably incorporated broad ideas from instructions but resisted precise control — related
- Small edits to cGPT instructions and knowledge bases had unpredictable effects on GPT responses during iterative co-design — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
continued-interaction-improves-cgpt-instruction-adherence |
title |
Students reported that continued interaction with a cGPT improved its adherence to instructions |
description |
Students reported that continued interaction with a cGPT improved its adherence to instructions |
status |
review |
evidence_strength |
weak |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — lo-s-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.