AI编程能力边界探索：基于 Claude Code 的 Spec Coding 项目实战｜得物技术

AI and live coding has been little explored. This article contributes with a short review of different perspectives of using virtual agents in the practice of live coding looking at past and present as well as pointing to future directions.

pynucastro addresses two needs in the field of nuclear astrophysics: visual exploration of nuclear reaction rates or networks and automated code generation for integrating reaction network ODEs. pynucastro accomplishes this by interfacing with nuclear reaction rate parameterizations published by the JINA Reaclib project (Cyburt et al. 2010).

In this paper, we give algorithms and methods of construction of self-dual codes over finite fields using orthogonal matrices. Randomization in the orthogonal group, and code extension are the main tools. Some optimal, almost MDS, and MDS self-dual codes over both small and large prime fields are constructed.

Self-dual codes are important because many of the best codes known are of this type and they have a rich mathematical theory. Topics covered in this survey include codes over F_2, F_3, F_4, F_q, Z_4, Z_m, shadow codes, weight enumerators, Gleason-Pierce theorem, invariant theory, Gleason theorems, bounds, mass formulae, enumeration, extremal codes, open problems. There is a comprehensive bibliography.