Abstract
End-user programmers, such as scientists and data analysts, communicate their intent through culturally specific, semi-formal representations like formulas and wireframes. Research on end-user programming interfaces has sought to democratize programming but has required advances in program synthesis, UI design, and computer vision to support translating a representation to code. As a result, end-users must still frequently translate such representations manually. Foundation models like ChatGPT and GPT-4V dramatically lower the cost of designing new programming interfaces by offering much better code synthesis, UI generation, and visual comprehension tools. These advances enable new end-user workflows with more ubiquitous semi-formal representations. We outline the translation work programmers typically perform when translating representations into code, how foundation models help address this problem, and emerging challenges of using foundation models for programming. We posit semi-formal and notational programming as paradigmatic solutions to integrating foundation models into programming practice. Articulating a design space of semi-formal representations, we ask how we could design new semi-formal programming environments enabled through foundation models that address their emergent challenges, and sketch “proactive disambiguation” as one solution to bridging gulfs of evaluation and execution.
| Originalsprog | Engelsk |
|---|---|
| Publikationsdato | 2024 |
| Status | Udgivet - 2024 |
| Begivenhed | PLATEAU: 14th annual workshop on the intersection of HCI and PL - University of California, Berkeley, USA Varighed: 19 feb. 2024 → … |
Konference
| Konference | PLATEAU |
|---|---|
| Lokation | University of California |
| Land/Område | USA |
| By | Berkeley |
| Periode | 19/02/2024 → … |