arXiv:2606. 07828v1 Announce Type: cross Abstract: I report a case study in AI-paired software engineering: five working ports of a vector illustration application across Rust, Swift, OCaml, Python, and browser-based platforms, built by a single developer in approximately 120 evening hours.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2608. 10450v1 Announce Type: cross Abstract: Complex software systems develop over timescales that exceed the lifespan of any individual coding agent.
arXiv:2608. 06640v1 Announce Type: cross Abstract: The widespread integration of AI coding assistants offers undeniable boosts to engineering velocity.
arXiv:2606. 30182v1 Announce Type: new Abstract: AI models are rapidly improving at autonomous coding, as shown by benchmark progress and one-off demonstrations such as AI implementing a C compiler.
arXiv:2606. 27045v1 Announce Type: cross Abstract: AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair.
arXiv:2604. 16399v3 Announce Type: replace-cross Abstract: Adoption of AI-assisted development in 2025 exposed a tool-agnostic failure pattern: experienced developers using frontier models were measurably slower while believing they were faster, and 10.
We’re releasing a human-validated subset of SWE-bench that more reliably evaluates AI models’ ability to solve real-world software issues.