Takhti: Researcher-directed software development with AI and open-source tools
Year: 2026
Type: preprint
Abstract: Writing in LaTeX usually involves moving between source and compiled output. Frequent compilation catches errors early, but also interrupts writing, particularly for long manuscripts and presentations. This paper describes how a high-energy physics researcher without professional software-engineering training developed Takhti with substantial assistance from ChatGPT and Codex. Initial versions automated conventional compilation; their limitations motivated an incremental live backend based on TeXpresso. The paper explains the checkpoint-and-replay approach, design decisions, and testing on a structured corpus of 81 arXiv source projects alongside other research and teaching documents. A frozen macOS assessment passed the defined interaction checks throughout that corpus, while later Windows tests retained unresolved failures and latency outliers.
Author: Iqbal, Shahin
Institution: Abdus Salam Centre for Physics
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7236302873
