arXiv subjects

Ke Mao

Publications and source records attributed to Ke Mao.

3 recordsLinked to original sources

arXiv2025

WhatsCode: Large-Scale GenAI Deployment for Developer Efficiency at WhatsApp

The deployment of AI-assisted development tools in compliance-relevant, large-scale industrial environments represents significant gaps in academic literature, despite growing industry adoption. We report on the industrial deployment of WhatsCode, a domain-specific AI development system that supports WhatsApp (serving over 2 billion users) and processes millions of lines of code across multiple platforms. Over 25 months (2023-2025), WhatsCode evolved from targeted privacy automation to autonomous agentic workflows integrated with end-to-end feature development and DevOps processes. WhatsCode achieved substantial quantifiable impact, improving automated privacy verification coverage 3.5x from 15% to 53%, identifying privacy requirements, and generating over 3,000 accepted code changes with acceptance rates ranging from 9% to 100% across different automation domains. The system committed 692 automated refactor/fix changes, 711 framework adoptions, 141 feature development assists and maintained 86% precision in bug triage. Our study identifies two stable human-AI collaboration patterns that emerged from production deployment: one-click rollout for high-confidence changes (60% of cases) and commandeer-revise for complex decisions (40%). We demonstrate that organizational factors, such as ownership models, adoption dynamics, and risk management, are as decisive as technical capabilities for enterprise-scale AI success. The findings provide evidence-based guidance for large-scale AI tool deployment in compliance-relevant environments, showing that effective human-AI collaboration, not full automation, drives sustainable business impact.

cs.SE↗

arXiv2025

Mutation-Guided LLM-based Test Generation at Meta

This paper describes Meta's ACH system for mutation-guided LLM-based test generation. ACH generates relatively few mutants (aka simulated faults), compared to traditional mutation testing. Instead, it focuses on generating currently undetected faults that are specific to an issue of concern. From these currently uncaught faults, ACH generates tests that can catch them, thereby `killing' the mutants and consequently hardening the platform against regressions. We use privacy concerns to illustrate our approach, but ACH can harden code against {\em any} type of regression. In total, ACH was applied to 10,795 Android Kotlin classes in 7 software platforms deployed by Meta, from which it generated 9,095 mutants and 571 privacy-hardening test cases. ACH also deploys an LLM-based equivalent mutant detection agent that achieves a precision of 0.79 and a recall of 0.47 (rising to 0.95 and 0.96 with simple pre-processing). ACH was used by Messenger and WhatsApp test-a-thons where engineers accepted 73% of its tests, judging 36% to privacy relevant. We conclude that ACH hardens code against specific concerns and that, even when its tests do not directly tackle the specific concern, engineers find them useful for their other benefits.

cs.SE↗

arXiv2022

Nature and Energy Source of the Strong Waveforms Recorded during the 2008 Wenchuan Earthquake

Earthquakes are indeed triggered by fault dislocations, but whether this process alone can produce the actual earthquake energy released by the mainshock has long been questioned. Therefore, exploring the true source of energy that causes earthquakes after the first motion is necessary. Based on analyses of the waveforms and ray paths at seismic stations close to the epicenter, it is considered that strong earthquake vibrations may not be caused by S-waves. It is also proposed that the reservoirs in sedimentary strata contain large amounts of high-pressure fluids, whose pressures can be released under certain conditions; this release of pressure may be an important component of the main earthquake energy. When a natural fault ruptures and penetrates a reservoir with a large area, the elastic energy produced by the release of pressure can reach the energy released by an earthquake of magnitude 8.0. Artificial engineering activities can lead to small-scale fluid pressure release phenomena, such as blowouts during drilling and earthquakes induced by hydraulic fracturing. Much direct and indirect evidence, such as the characteristics of seismic waves in the time and frequency domains recorded during the Wenchuan earthquake, explosion phenomena observed on the ground and cores obtained by scientific drilling, indicates the possibility of such energy release. We propose that seismicity can be divided into three stages: the microfracturing stage, in which there is fluid activity and can produce an electrokinetic effect; the significant fracturing stage after the initial movement; and the strong earthquake stage caused by fluid pressure release.

physics.geo-ph↗