Max

[Thariq @trq212]

https://t.co/R6exTuF7P8

[Thariq @trq212]

been asking others at Anthropic how they stay in the loop with Claude and fully understand the work being done

this is one of my favorites from Suzanne:

[cat @_catwu]

Excited to share our most powerful new Claude Code feature: dynamic workflows!

Mention "workflow" in a prompt and Claude will dynamically create an orchestration plan that it strictly follows, allowing you to confidently trust that every stage happens in the right order even across 100s of agents.

[Mitchell Hashimoto @mitchellh]

I've got an agent in a loop optimizing a renderer with the goal to minimize frame times (and tests to measure). It got times down from 88ms to 2ms and allocations down from ~150K to 500. Sounds good, right? Wrong. This is exactly why agent psychosis is a big fucking problem.

As an experiment, I rewrote the Ghostty core render state in Go, with access to identically laid out data structures as Ghostty and the exact same validation tests. I made a purposely naive renderer (simple, correct, but slow). 88ms per frame with 150,000 allocations (horrendous, lol)!

I then kickstarted a Ralph loop to bring the frame times down. I told it it can't modify input data structures or the public API or tests (they're correct), but it can do anything else it wants. It got to work.

It has worked for about 4 hours. I've spent around $350 on this experiment so far. The results?

88ms => 1.5ms
150K allocs => ~500 allocs

Incredible right? Nope.

My hand-written renderer I ported has frame times (same benchmark) of ~20us (0.020ms) and 0 allocations in the update path.

This is the problem with psychosis and lacking systems understanding. If you don't understand the system, you're going to accept that this is an incredible result. If you understand the system, you'll see better solutions immediately and can do roughly 75x better on throughput.

The people who blindly trust agent output are in the former camp. They're sheeple, overdrinking from a fountain of mediocrity.

Standard disclaimer: I use AI all the time. I like AI. The point I'm making is to not blindly accept results. Think. Analyze. Learn.

[ClaudeDevs @ClaudeDevs]

New in Claude Code (research preview): dynamic workflows.

Claude writes an orchestration script on the fly, then spins up a large fleet of coordinated subagents in parallel to take on your most complex tasks.

Use the word "workflow" in a prompt to get started.

[Claude @claudeai]

New in the Claude Marketplace: @augmentcode, @boltdotnew, @coderabbitai, @hebbia, and @WeAreLegora.

Apply your existing Anthropic spend commitment toward their Claude-powered products.

Learn more: https://t.co/J3Sdsg2lU6

[ClaudeDevs @ClaudeDevs]

We’ve been putting a lot of effort into making Claude Code more responsive & reliable.

Here’s an update on everything we’ve done:

[Lydia Hallie ✨ @lydiahallie]

To add some clarity: you don't pay extra. It's the same subscription, same price per month.

What's new our sub now covers two separate pools:

· Interactive → sub limits, unchanged
· Programmatic → new $20–$200 included(!!) credit, metered at API rates

[ClaudeDevs @ClaudeDevs]

Claude Code weekly limits are increasing 50%, now through July 13.

Live now for all Pro, Max, Team, and seat-based Enterprise users.

[Boris Cherny @bcherny]

People often ask what my biggest tip is for getting the most out of Claude Code.

These days my #1 tip is: use auto mode

Auto mode means no more permission prompts. It is the key building block for multi-clauding: start a session, then while it runs, work on another session in parallel.

[Thariq @trq212]

a prompt I've been using a lot recently:

implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

[Movez @0xMovez]

This 30-minute speech by the Head of Anthropic "Coding Agents" researcher will teach you more about vibe coding than 100 paid courses.

Bookmark it & give it 30 minutes today. This video will change the way you use AI forever,

[Boris Cherny @bcherny]

Dogfooding Opus 4.7 the last few weeks, I've been feeling incredibly productive. Sharing a few tips to get more out of 4.7 🧵

[Noisy @noisyb0y1]

https://t.co/L5nfhxin3p

[Ryan Peterman @ryanlpeterman]

Boris Cherny (Creator of Claude Code): "The one technical book I would recommend to everyone that has had the greatest impact on me as an engineer is functional programming in Scala.

You're probably never going to use Scala day today, but the way it teaches you to think about coding problems is just such a change from the way that most people were in coding, either practically or in school. It's just. It's incredible. It's going to completely change the way that you code now.

I think in types, when I code, the thing that matters in your code the most is the type signatures. This is more important than the code itself." @bcherny

[Claude @claudeai]

We're bringing the advisor strategy to the Claude Platform.

Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

[Noah Zweben @noahzweben]

Thrilled to announce the Monitor tool which lets Claude create background scripts that wake the agent up when needed.

Big token saver and great way to move away from polling in the agent loop

Claude can now:
* Follow logs for errors
* Poll PRs via script
* and more!

[岛 @Ni_luvya]

昨天看完了OpenAI 工程师翁家笠 @Trinkle23897 的访谈，给我最大的感受就是他求知欲旺盛、学习能力很强。

他在 2022 年加入 OpenAI，并且是 OpenAI 一系列核心模型背后的核心贡献者之一，从 GPT-3.5、GPT-4、再到 GPT-5，你能看到的那些关键跃迁里，都有他的身影。他最主要的贡献，是以下三个词：强化学习、post-training、infra。

我在他的个人网站里搜到的经历见图一，下面是看完整期播客的一些感受：

🍃一、求知欲强且找到了自己的学习方法：

发现自己需要更长的时间构建知识树，需要比常人花2-3倍时间去理解context和底层逻辑。

他的学习的兴趣从何而来？他认为这是对自己的投资、对未来的投资。

并且在学习的过程中他会通过正反向筛选来构建自己的技能树：
1. 正向筛选就是他很早就发现自己喜欢奥数，并且持续投入能获得比别人更快的成就。
2. 同时会果断放弃投入比产出低的，例如打篮球，经常被别人按着打；例如跆拳道，实战会被揍；对语文不感兴趣等等。

虽然学得慢，但他找到了适合自己的学习方式：
1. iPad的Safari没有代码编辑器，他用iPad裸打代码，其实是完全不必要的，不过这种方式强迫他在大脑中构建程序逻辑，训练他的思考和反应能力。
2. 学得慢就提前学。比如初二学完高中数学，初三开始学微积分。
3. GPA不重要，短时间达到够用的成绩就行，不浪费时间。学对自己重要的东西。

🍃二、构建自己的评价体系：
当他意识到清华内部大家都认为GPA越高越好、PhD远比Master好，并为之奋斗的时候，他认为自己的目标是找工作，GPA选择在最少时间达到够用的成绩就行，重点在于在行业里积累经验。

他认同自己导师的评价指标：论文、比赛、三位数以上的GitHub Star

在清华期间开源自己搜集的所有作业和材料，打破信息差。因为他认为有些人不擅长搜索，但很有能力，不必要浪费时间在这上面。

他希望获得认可，如Github的star数，如最大化自己在OpenAI blog上出现名字的次数，只要他在RL，每个大模型发blog都尽可能能带上名字，从而实现生产力的scale up ，让自己的工作量转化为所有核心产品的贡献。

🍃三、在人生节点，他是如何做决策的：

1. 为什么不读PhD：前面提到的，跟之前提到他的价值体系有关，认为自己要进入工业界而不是学术界，“教一个researcher做好enginerring, 要远比教一个engineer如何做好research难得多”，因此他就不需要PhD来浪费生命，更看重Infra.

2. 在ChatGPT爆发前，为什么手握OpenAI、幻方、谷歌、英伟达的offer，选择了OpenAI: 不想进谷歌，不愿意当螺丝钉，他想进人才密度最高的地方，当时到幻方做RL infra是备选。

🍃四、主播也很会提问题，例如大家都在吐槽OpenAI已经不open了，翁家笠他也曾经一直在做开源相关的事��，这不冲突吗？

对于OpenAI 这样的大模型公司来说生死线是infra迭代的时间。现阶段不进行闭源就无法持续融资，解决算力成本和实验开销，从而推动技术。

他说其实John Schulman曾经问过是否将RL Infra开源，但为了公司竞争力和安全性，还是拒绝了。也就是现阶段他调整了个人优先级，尽管曾通过开源天授、退学Online签证查询系统来打破信息差，但认同现阶段顶尖模型公司需要通过闭源来做博弈。

如果未来创业，他大概会选择产品方向。因为他认为技术的复杂程度不重要，能精准抓到用户需求才重要。退学Online在早期甚至是手动更新，但解决了他们的燃眉之急（他做过的项目介绍见图二）。他自己对纯研究、发论文没什么兴趣，更喜欢有多少人记得、使用他做的东西。

🍃五、主播问到：”如果AI能解决一个世界难题，他希望解决什么？““如何预测未来” 由此展开了宿命论的探讨

他认为这个世界是个确定论，人的命运是可以被预测的，我们生活在一个确定性的马尔可夫过程里（播客对我这种小白来说很友好，专业术语都有解释，如果你也需要可以看图三、图四）需要提前生成剧本。

他甚至认为，人是没有自由意志的，大脑里在想什么，对话中下一个单词说什么、问什么问题都是宇宙大爆炸的那一刻就确定了。

主持人真的很会提问！下一个问题是如果是宿命论那为什么他要投资未来：
1. 未来的我帮助过去的我，完成某些决策。所以要投资自己，投资未来 例如他自己在高三蹦出的“要创造影响力”的想法，是未来的他给过去的自己发送的信息
2. 秉持宿命论，他的生存策略不是等待一切线性结果的到来，而是忘掉这一切，假装不知道，然后尽情享受人生体验。坚信西西弗斯是幸福的，活着是在确定性的循环里寻找当下的意义。

原播客不太长，只有2小时。地址：https://t.co/HbQb0I7gcB

[Aakash Gupta @aakashgupta]

Anthropic just mass-obsoleted every agent orchestration startup in a single launch.

The screenshot tells the full story. That's a production fleet dashboard. 8 agents running. 247 completed tasks. Active status. MCP-connected to HubSpot, pulling deals, generating proposals, reading attachments. This isn't a demo. It's a managed production environment where you define the agent and Anthropic runs the infrastructure.

The timing here is surgical. Four days ago, Anthropic blocked OpenClaw and every third-party harness from using subscription credentials. The message was clear: stop building on top of our consumer auth layer. Now here's the replacement. A first-party managed agent platform with fleet monitoring, production-grade MCP integrations, and prototype-to-launch timelines measured in days.

Manus spent six months on five harness rewrites. LangChain spent a year on four architectures. Anthropic just shipped the managed version that eliminates the need to build one at all.

The real bet: most companies don't want to build agent infrastructure. They want agents that work. Anthropic is pricing this into the platform the same way AWS priced server management into EC2. The 46% of enterprises citing "integration with existing systems" as their primary agent challenge just got a first-party answer from the model provider itself.

Every agent startup that raised on "we make Claude reliable in production" just lost their pitch deck.

[Andrej Karpathy @karpathy]

LLM Knowledge Bases

Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So:

Data ingest:
I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them.

IDE:
I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides).

Q&A:
Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale.

Output:
Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base.

Linting:
I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into.

Extra tools:
I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries.

Further explorations:
As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows.

TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.