大模型写代码常“编造”不存在依赖包？这篇论文系统评估了推理时防御手段，帮你避开代码幻觉坑。
arXiv:2608.22652v1 Announce Type: cross Abstract: LLMs are increasingly used for code generation, yet they frequently hallucinate non-existent softwar…
揭秘架构如何成为编码智能体的能力均衡器，为提升代码生成质量提供新视角。
arXiv:2608.21747v1 Announce Type: cross Abstract: LLM-based coding agents generate complete software systems from high-level descriptions, yet little …
AI编程助手的安全短板怎么补？这篇论文用Terok环境给出了可落地的防护思路。
arXiv:2608.22930v1 Announce Type: new Abstract: Agentic AI is a fascinating new tool for software development. It is a huge step forward compared to "…
从系统设计视角拆解AI Agent构建，借Bob大叔观点快速提升设计敏感度，直击编码Agent的软肋。
Coding with agents really has surfaced a bunch of problems and challenges we never ran into when writing code by hand. Agents work even faster than yo…
揭秘AI圈“自我舔舐”陷阱：用LLM解释LLM，代码生成的测试金标准还能可信吗？
Article URL: https://daviesgeek.com/I-Shouldn%E2%80%99t-Need-an-LLM-to-Explain-My-LLM Comments URL: https://news.ycombinator.com/item?id=49409282 Poin…
用对话式AI驱动终端编程，能自动分析、写码并调试，快速搞定驱动等复杂开发任务。
IT之家 8 月 21 日消息，据外媒 neowin 报道，一名青少年开发者 Kuber Mehta 利用 Anthropic 的 Claude Code，为一款缺乏 macOS 官方支持的惠普激光打印机开发出了原生驱动，展示了 AI 编程工具在解决冷门硬件兼容问题上的潜力。 ▲ HP Laser …
定义一次模型，自动生成可读的Go CRUD代码，无需反射，效率与可维护性兼得。
Been building goninja , a Go framework that generates CRUD REST APIs from annotated structs — routing, validation, OpenAPI, the rest. It's the Go coun…
用测试驱动推理重塑代码生成流程，TDD-Agent为AI编程提供新范式
arXiv:2608.16742v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring corr…
2026年实证研究：生成式AI在入门面向对象编程测评中的表现是否提升？对比历年数据，洞察AI编程能力演进与教学建议。
arXiv:2608.16318v1 Announce Type: cross Abstract: Recent advances in Generative Artificial Intelligence (GenAI) have substantially improved the abilit…
一项实证对比发现，用ISO标准结构化非功能需求描述，能显著提升LLM生成代码的质量，提示工程优化有新思路。
arXiv:2608.13742v1 Announce Type: cross Abstract: In LLM-based code generation, Non-Functional Requirements (NFRs) are often specified as terse one-li…
AI 编程助手融入 SpaceX 算力，代码智能生成与理解再升级，极客必备。
AI coding startup Cursor is now officially a part of SpaceX.
代码大模型靠记忆还是真理解？这项研究揭示传统记忆化探针在大规模模型上严重失效，诊断方法必须随规模调整。
arXiv:2608.12771v1 Announce Type: cross Abstract: The extent to which large language models for code rely on memorization over genuine understanding r…
别让AI替你写代码，用它当导航地图，避开生成陷阱，真正提效
The trap of the 'Generate' button When I first started using AI-powered editors like Cursor, I fell into the same trap as everyone else. I would write…
一句提示词搞定代码生成与调试，AI驱动的编程助手正重塑开发流程
IT之家 8 月 14 日消息，SpaceX 完成了对 AI 编程初创公司 Cursor 的 600 亿美元 （IT之家注：现汇率约合 4,054.22 亿元人民币） 收购。 对于马斯克而言，这笔交易是追赶 Anthropic 和 OpenAI 的重要一步。监管文件显示，收购于当地时间 8 月 14…
揭秘AI如何写物理动画代码，新基准测试与训练方法一睹为快。
arXiv:2602.10840v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely studied in areas such as mathematical reasoning, com…
资深工程师如何在不拥抱生成式AI的境况下保持专业竞争力？一场关于技术信仰与时代浪潮的真诚讨论。
Context: I don't like LLMs and code generators. I prefer doing things the old-fashioned way – code using my brain, write design docs while doing resea…
越聊越笨不怪你：上下文腐烂正悄悄拖垮AI Agent的会话质量，开发者的信任危机值得警惕。
Originally published at getunblocked.com on August 10, 2026. Context rot is the gradual degradation of an LLM's output quality as its context grows — …
LLM代码通过测试就够了吗？新基准揭示隐藏的意图违背问题。
arXiv:2608.07614v1 Announce Type: cross Abstract: Code generated by LLMs can violate a developer's implicit intentions when given an ambiguous prompt,…
用 LLM 重写经典终端特效库，AI 生成代码能还原多少视觉魔法，值得一看
Article URL: https://github.com/omacom-io/ttfx Comments URL: https://news.ycombinator.com/item?id=49243229 Points: 4 # Comments: 1
让编程智能体实时纠偏，在线监控与纠正引导新框架，大幅提升代码生成可靠性。
arXiv:2608.06701v1 Announce Type: cross Abstract: Fixing GitHub issues in large-scale projects is a long-horizon task, especially when a fix requires …