1
Show HN: We Built OpenClaw but Worse
自称“比OpenClaw还差”，反向营销的幽默项目，值得一探究竟。
Article URL: https://www.supafax.com/ Comments URL: https://news.ycombinator.com/item?id=48109067 Points: 4 # Comments: 0
2
Node.js 0.8.28 (Maintenance)
Node.js 0.8.28维护版本发布，修复v8中断掩盖栈溢出关键bug
3
Version 0.6.21 (maintenance)
Node.js 0.6.21 维护版发布，修复 SunOS 和 socket 连接问题，适合历史版本兼容场景。
4
openclaw 2026.5.16-beta.7
openclaw项目发布2026.5.16-beta.7预发布版本，拥有37.3万星标，值得关注最新更新。
Changes Dependencies: update @openclaw/proxyline to 0.3.3. Dependencies: update Pi packages to 0.75.1 and raise the minimum supported Node.js 22 line …
5
Pain of Manual Memory Forensics
手动内存取证的痛点：自动化还是坚持手动？技术讨论等你参与。
Do you automate your memory forensics work? If yes, How? If no, Why? Comments URL: https://news.ycombinator.com/item?id=48193226 Points: 2 # Comments:…
6
Managing Node.js Dependencies with Shrinkwrap
教你用shrinkwrap锁定Node.js依赖版本，但已过时，建议看lockfile文档
7
Team update
OpenAI迎来新成员，团队持续扩张，同时公开招聘中。
We’d like to welcome the latest set of team members to OpenAI (and we’re still hiring!)
8
openclaw 2026.5.18-beta.1
开源项目 openclaw 发布 2026.5.18-beta.1 预发布版，但页面加载失败无详细内容。
Changes Agents: clarify that fixes should default to clean bounded refactors, lean internals, and explicit plugin SDK/API deprecation paths. Dependenc…
9
openclaw 2026.5.16-beta.6
开源工具openclaw推出2026.5.16-beta.6版，因加载异常暂无具体更新细节，可关注release页面
Changes Mac app: redesign Settings pages with consistent card layouts, cached navigation, cleaner permissions/voice/skills/cron/exec/debug panes, and …
10
A股三大指数集体低开，湖南白银跌超3%
提供的页面仅为网站导航栏，缺少文章正文内容，无法生成推荐语和评分。
36氪获悉，A股三大指数集体低开，沪指低开0.37%，深成指低开0.62%，创业板指低开0.87%；贵金属、稀土、海运板块跌幅居前，招商轮船跌超4%，湖南白银跌超3%，中国稀土跌超2%；HBM、氟化工、存储器概念领涨，中欣氟材涨超9%，雅克科技涨超9%，兆易创新涨超8%。
11
eBPF 介绍
从BPF到eBPF，一文讲透Linux内核观测性利器，附赠彩蛋。
很早前就想写一篇关于eBPF的文章，但是迟迟没有动手，这两天有点时间，所以就来写一篇，这文章主要还是简单的介绍eBPF 是用来干什么的，并通过几个示例来介绍是怎... Read More Read More The post eBPF 介绍 first appeared on 酷 壳 - CoolS…
12
Prompting fundamentals
OpenAI官方教程，掌握提示词基础，让ChatGPT输出更精准有用。
Learn prompting fundamentals and how to write clear, effective prompts to get better, more useful responses from ChatGPT.
13
GPT-5.3-Codex System Card
OpenAI最强编程模型GPT-5.3-Codex发布，融合前沿编码与推理能力，效率惊人
GPT‑5.3-Codex is the most capable agentic coding model to date, combining the frontier coding performance of GPT‑5.2-Codex with the reasoning and prof…
14
Introducing GPT-5 for developers
OpenAI正式发布GPT-5 API，推理性能飞跃，专为开发者打造，编码任务表现最佳。
Introducing GPT-5 in our API platform—offering high reasoning performance, new controls for devs, and best-in-class results on real coding tasks.
15
Improved Techniques for Training Consistency Models
OpenAI改进一致性模型训练，突破一步生成高质量样本，无需对抗训练
Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training.
16
GPT-4V(ision) system card
OpenAI官方发布GPT-4V系统卡，详解多模态模型能力、安全评估与局限性。
17
GPT-3.5 Turbo fine-tuning and API updates
OpenAI官方宣布GPT-3.5 Turbo支持开发者带入数据进行微调定制，重磅API更新。
Developers can now bring their own data to customize GPT-3.5 Turbo for their use cases.
18
Dew Drop – May 14, 2026 (#4668)
最新一期Dew Drop汇总了.NET 11的Process API改进、MAUI迁移至CoreCLR、GitHub Copilot CLI定制、AI系统调试思考等硬核技术更新，开发者必读。
Top Links Process API Improvements in .NET 11 (Adam Sitnik) .NET MAUI Moves to CoreCLR in .NET 11 (David Ortinau) Trick out your GitHub Copilot CLI wi…
19
MathAtlas: A Benchmark for Autoformalization in the Wild
首个大规模研究生级数学自动形式化基准，52k样本填补研究级数学空白。
arXiv:2605.14061v1 Announce Type: new Abstract: Current autoformalization benchmarks are largely focused on olympiad or undergraduate mathematics, whi…
20
Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
解决LLM重复任务中随机性失败与高成本痛点，LOOP引擎通过一次录制和确定性重放实现99%成功率并减少99%token消耗。
arXiv:2605.14237v1 Announce Type: new Abstract: Deploying AI agents for repetitive periodic tasks exposes a critical tension: Large Language Models (L…