QCon Shanghai 2023: LLM-Powered Frontend Debugging, WebNN, AI-Native Development, and HarmonyOS Insights
QCon Shanghai 2023 highlighted LLM‑driven frontend debugging, the emerging WebNN API for accelerated browser inference, AI‑native UI patterns with evaluation‑driven development, LLM‑enhanced developer bots using RAG and fine‑tuning, and a HarmonyOS round‑table exploring ArkUI’s declarative framework and opportunities for frontend engineers.
This article summarizes the QCon Shanghai 2023 conference, focusing on four main technical tracks: LLM-powered frontend debugging, WebNN for browser-based neural network inference, AI-native frontend development patterns, and using LLMs to improve developer Q&A experiences.
The first track presents an AI-assisted debugging approach that combines record&replay, program slicing, and large language models to locate defects efficiently, discussing trade-offs between data collection costs and debugging efficiency for long‑standing issues.
The second track introduces the Web Neural Network API (WebNN), its standardization progress, hardware acceleration via NPU, and sample code showing how to import an ONNX model with import { InferenceSession } from "onnxruntime-web" .
The third track explores AI‑native interaction models, UI extension plugins, and evaluation‑driven development (EDD) for improving user experience in AI‑powered applications.
The fourth track describes a LLM‑enhanced developer support bot that uses RAG and fine‑tuning, automatic FAQ generation, and text‑chunking strategies to overcome model context limits.
Additionally, the article covers a round‑table discussion on HarmonyOS, detailing its ecosystem growth, the ArkUI declarative framework based on ArkTS, and opportunities for frontend developers in the emerging native HarmonyOS landscape.
DeWu Technology
A platform for sharing and discussing tech knowledge, guiding you toward the cloud of technology.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.