第69期 | openai/openai-cookbook
今日摘要
OpenAI Blog：OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-runn…
OpenAI Blog：OpenAI expands its Trusted Access for Cyber program, introducing GPT-5.4-Cyber to vetted defenders and strengthening safeguards as…
OpenAI Blog：Cloudflare brings OpenAI’s GPT-5.4 and Codex to Agent Cloud, enabling enterprises to build, deploy, and scale AI agents for real-w…
OpenAI Blog：Learn how sales teams use ChatGPT to research accounts, personalize outreach, manage deals, and improve pipeline and conversion.
OpenAI Blog：Learn how to use ChatGPT, start your first conversation, and discover simple ways to write, brainstorm, and solve problems with AI…
总结 + 观点：Someone recently suggested to me that the reason…｜中文观点：围绕 R to @karpathy: Someone recently suggested…
总结 + 观点：Judging by my tl there is a growing gap in under…｜中文观点：从 Judging by my tl there is a growing gap in…
总结 + 观点：Karpathy 新发布的最小 ChatGPT 复现项目，训练到推理的完整栈只有几千行可读代码，…｜中文观点：nanochat 最值得看的不是性能，而是它第一次把 ChatGPT 训练+推理的全流程压…
总结 + 观点：Karpathy 早期的教学级 GPT 实现，代码短到可以一口气读完，长期用作理解 Transf…｜中文观点：minGPT 的价值不是生产就绪，而是教材级清晰：它最适合那些想从零搭一遍训练循环、确认自…
总结 + 观点：Anthropic 公开其内部工程师 take-home 面试题，可作为理解他们工程品味和评估标…｜中文观点：这条的信号不是题目本身，而是 Anthropic 把招聘标准开放出来，对想了解他们工程文化…
The next evolution of the Agents SDK
标签：#ai_engineering_blogs #core
作者：
原文：OpenAI updates the Agents SDK with native sandbox execution and a model-native harness, helping developers build secure, long-running agents across files and tools.
链接：https://openai.com/index/the-next-evolution-of-the-agents-sdk
Trusted access for the next era of cyber defense
标签：#ai_engineering_blogs #core
作者：
原文：OpenAI expands its Trusted Access for Cyber program, introducing GPT-5.4-Cyber to vetted defenders and strengthening safeguards as AI cybersecurity capabilities advance.
链接：https://openai.com/index/scaling-trusted-access-for-cyber-defense
Enterprises power agentic workflows in Cloudflare Agent Cloud with OpenAI
标签：#ai_engineering_blogs #core
作者：
原文：Cloudflare brings OpenAI’s GPT-5.4 and Codex to Agent Cloud, enabling enterprises to build, deploy, and scale AI agents for real-world tasks with speed and security.
ChatGPT for sales teams
标签：#ai_engineering_blogs #core
作者：
原文：Learn how sales teams use ChatGPT to research accounts, personalize outreach, manage deals, and improve pipeline and conversion.
Getting started with ChatGPT
标签：#ai_engineering_blogs #core
作者：
原文：Learn how to use ChatGPT, start your first conversation, and discover simple ways to write, brainstorm, and solve problems with AI.
Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical pe...
标签：#x_profiles #extended
作者：
原文：Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical people (who otherwise only knew AI as synonymous with ChatGPT as a website) experienced the latest agentic models.
Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use.
标签：#x_profiles #extended
作者：
原文：Judging by my tl there is a growing gap in understanding of AI capability. The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code. But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much value. The goldmines are elsewhere, and the focus comes along. So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions. TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are. staysaasy (@staysaasy) The degree to which you are awed by AI is perfectly correlated with how much you use AI to code. https://nitter.net/staysaasy/status/2042063369432183238#m
karpathy/nanochat
标签：#github_orgs #extended
作者：
原文：Karpathy 新发布的最小 ChatGPT 复现项目，训练到推理的完整栈只有几千行可读代码，目标是把“百美元跑一个 ChatGPT”压到个人可动手的范围。
karpathy/minGPT
标签：#github_orgs #extended
作者：
原文：Karpathy 早期的教学级 GPT 实现，代码短到可以一口气读完，长期用作理解 Transformer 训练与推理最短路径的入口。
anthropics/original_performance_takehome
标签：#github_orgs #extended
作者：
原文：Anthropic 公开其内部工程师 take-home 面试题，可作为理解他们工程品味和评估标准的一手材料。
链接：https://github.com/anthropics/original_performance_takehome
openai/symphony
标签：#github_orgs #extended
作者：
原文：OpenAI 新开源的多 agent 编排框架，重点不是写代码的 coding agent，而是任务隔离、委派与团队级协作。
openai/openai-cookbook
标签：#github_orgs #extended
作者：
原文：OpenAI 官方示例库更新，通常折射出他们希望开发者优先采用的新模式（tool use、structured output、responses API 等）。
karpathy/rustbpe
标签：#github_orgs #extended
作者：
原文：Karpathy 用 Rust 重写的 BPE tokenizer 训练器，把 tiktoken 里不透明的训练流程变成可学习、可实验的代码。
openai/openai-python
标签：#github_orgs #extended
作者：
原文：OpenAI 官方 Python SDK 更新，通常先于公告暴露出新接口细节、参数变化或默认路径调整。
anthropics/claude-agent-sdk-demos
标签：#github_orgs #extended
作者：
原文：Anthropic 官方的 Claude Agent SDK 示例仓库，覆盖代码 agent、文件编辑、工具链编排等典型用法。
Sightings
标签：#ai_engineering_blogs #core
作者：
原文：/elsewhere/sightings/ I have a new camera (a Canon R6 Mark II) so I'm taking a lot more photos of birds. I share my best wildlife photos on iNaturalist and based on yesterday's successful prototype I decided to add those to my blog. I built this feature on my phone using Claude Code for web, as an extension of my beats system for syndicating external content. Here's the PR and prompt. As with my other forms of incoming syndicated content sightings show up on the homepage, the date archive pages, and in site search results. I back-populated over a decade of iNaturalist sightings, which means you that if you search for lemur you'll see my lemur photos from Madagascar in 2019! Tags: blogging photography wildlife ai inaturalist generative-ai llms ai-assisted-programming claude-code
链接：https://simonwillison.net/2026/May/2/sightings/#atom-everything
AI Engineer World's Fair Autoresearch, Memory, World Models, Tokenmaxxing, Agentic Commerce, and Vertical AI Call for Speakers
标签：#ai_engineering_blogs #core
作者：
原文：a quiet day lets us make a call for speakers!
链接：https://www.latent.space/p/ainews-ai-engineer-worlds-fair-autoresearch
Ask HN: Any nice project ideas that you know you'll never bring to life
标签：#research_community #extended
作者：
原文：Every now and then a nice web/mobile application pop into my head. But because of my day job and a side project I’m currently working on, I already know that this idea will never come to life. Do you just write them down and move on and maybe eventually forget about it? Share them publicly? If you share them and someone else brings the idea to life, would that make you happy? Curious what's your approach? Comments URL: https://news.ycombinator.com/item?id=47981506 Points: 1 Comments: 0
New study finds task switching raises risk in transplant surgeries
标签：#research_community #extended
作者：
原文：Article URL: https://news.vt.edu/articles/2026/04/pamplin-bit-research-organ-transplant-task-switching.html Comments URL: https://news.ycombinator.com/item?id=47981486 Points: 1 Comments: 0
链接：https://news.vt.edu/articles/2026/04/pamplin-bit-research-organ-transplant-task-switching.html
GameStop is preparing offer for eBay
标签：#research_community #extended
作者：
原文：Article URL: https://finance.yahoo.com/markets/stocks/articles/gamestop-preparing-offer-ebay-wsj-212703455.html Comments URL: https://news.ycombinator.com/item?id=47981465 Points: 1 Comments: 0
链接：https://finance.yahoo.com/markets/stocks/articles/gamestop-preparing-offer-ebay-wsj-212703455.html