Announcing the book "𝑀𝑎𝑠𝑡𝑒𝑟𝑖𝑛𝑔 𝑎𝑠𝑡-𝑔𝑟𝑒𝑝"!🦉 The book is a structured deep-dive: we start with the mental models of ASTs, move to rule composition, and end with advanced usage. It’s the place where design principles and philosophy are explained. Link below ↓

Hey, I joined the VoidZero team! I'm still at Cloudflare — VoidZero is part of Cloudflare! — and will continue as a Developer Advocate. I'll also work on synergy between Hono and VoidZero products like Vite, Vite+, Oxc, and Void, and advocate for them!

把童年回忆里的宝石迷阵移植到 Mac 上了。之前试过 Wine / CrossOver 因为各种原因都没有成功把它跑起来，抱着试试看的心态让 Opus 5.5 又搞了一次，竟然真的可以玩了。 过程还是很曲折的，最简单的部分是 Windows 和各种库的 HLE ，很快就能把游戏跑起来了。但是 x86 模拟用的是 Unicorn（当时觉得完整逆向游戏，然后用 C++ 重写会更复杂，验证起来也不容易），很快遇到了性能瓶颈，帧率只有个位数。然后 Opus 5.5 profile 了热点函数之后自己写了一个 lifter，并且验证了 AOT 部分的逻辑与 Unicorn 模拟运行的是一致的，整个过程非常的系统化。 考虑到 Rosetta 马上就 sunset 了，感觉这个研究还是挺有意义的，以后有时间会继续探索一下。

wow X is blocking agent reading with 402 Payment Required

lol opus5.5 built a repl for my toy language overnight

Bond Warrior Bessent-San

Sunset Paints NYC❤️‍🔥 Drop a photo of the sunset where you are👇

New York City on the eve of Nor’easter

Following our discussions about Muse last week and the release of our report on Monday, we received a lot of questions. 1. Can OpenAI and Gemini build a personal agent as good as Muse? We’ve spoken with quite a few researchers and teams building personal agents. Our main takeaway is that success depends less on the gap between models today and more on how seriously a company commits to the product: how many people it puts behind it, how much it spends, and how quickly it learns from users. In some ways, this feels like the early debate around Manus. The model matters, but so does all the work around it. You need a large team to understand what people actually want, improve individual use cases, and get the agent working reliably with other apps. One difference already stands out to us: Muse feels more like a consumer product, while the alternatives feel more like productivity tools. That distinction matters. Helping people with everyday needs is a different challenge from helping them get more work done. It’s also expensive. Beyond the product and integration work, there’s the compute bill. Based on what we’ve learned, running the service currently costs roughly $15–20 per DAU per month. There haven’t been many breakout consumer products in the US lately. But when Zuckerberg sees an opportunity like this, he tends to go all in. We think Meta has a better shot here than it did in VR or in the race to build the best AI models. Understanding users, refining use cases, and putting substantial resources behind a product are things Meta does well. 2. How do we think about Muse’s ROI? The biggest opportunity, in our view, is better purchase-intent data: a clearer understanding of what users are considering buying. In our best-case scenario, those additional signals could lift revenue by 25%. Using our estimate of roughly $50 in US revenue per DAU, that would mean another $12.50. Costs also have room to come down. We think better efficiency could eventually bring Muse’s running cost to around $10 per DAU per month. If Meta can get there, the advertising upside, together with other potential revenue streams, could more than cover the cost—even without a subscription fee. 3.Could Muse take ad share from Google? We think it could over time, but we don’t expect a meaningful impact over the next year. Muse gives Meta more purchase-intent data—a clearer picture of what users are actively considering buying. Over time, those signals could help Meta close the gap with Google in categories like travel, auto, and finance, and win some of the ad spending that currently goes to Google. But that will take time. Muse needs to build a regular user base, and Meta needs to turn those signals into better results for advertisers. We see this as a longer-term opportunity, not a near-term threat to Google’s ad business. 4. Can Tencent and Alibaba build a personal agent that is just as valuable? We don’t see the same incremental revenue opportunity in China, at least based on Muse’s current use cases. Many of those use cases address problems that are less common in China. Customer service is already efficient, for example, so people have less need for an agent that spends time making calls on their behalf. Tencent can also identify purchase intent much earlier through its existing apps and services. A personal agent may therefore add less information than it would for Meta. That doesn’t mean Tencent or Alibaba can’t build a useful product. But we wouldn’t assume the same revenue upside we see for Muse.

Opus 5.5 got my ts-rust port working in 10 hours, and it has been grinding on performance for the last 24 hours. I've been working on this port on and off for about 4 months. I got to ~35% tests passing with GPT-5.6 Sol, and ~85% with GPT-6 Astra. Both models stalled hard once hitting those numbers, and ran in loops with no meaningful progress for days at a time. I've never had "enough Anthropic tokens" to try a Claude model on a port like this. Opus 5.5 feels practically unlimited, so I threw it a "/goal finish the port and make it faster". I can not believe how quickly Opus unblocked the work Astra was stuck on. It may have made this port an actually viable project. Absolutely mind blown right now.

ボンド戦士ベッセントさん

ボンド戦士ベッセントさん

You just need bigger space, for both your disk and your home office

If coding agents will write most of our code, what happens with our communities and sense of ergonomics? How does it impact our compilers and tools?

Debate on cause of rise of the long term bond yields: Two models, both produced by economists affiliated with the Fed: 1) ACM (it’s all real yields/growth/ppl expect Fed to hike) 2) KM (it is term premium) Warsh picked the former interpretation. As did the rest of the FOMC, implied in the SEP More than a year ago, debate on whether tariffs would generate persistent vs transitory inflation: Two models also from Fed affiliated economists: 1) tariffs generate persistent inflation (new research) 2) tariffs deflationary in the long term, and initially a one off price change (from a long standing structural model that proved to be correct in 2018) The FOMC adopted the first interpretation, until facts showed otherwise today. Tell me that economics is not a dismal science. At least the Fed should debate about this, disagree. That is not what the SEP show. Group think is rearing its ugly head inside the Fed again.

why so many terminal apps have their own way to copy text?? turbo repo: C claude code: select codex: cmd-c every time i need to remember how to just copy the text 🤬

Opus 5.5 is good😀

$META $QQQ

Your new meme template

I am looking forward to reading the @AnthropicAI S-1 risk factors. Why won’t the first risk factor have to be: “Our senior management believes that there is a more than 10% chance that AI will kill all humans, which will likely cause our revenues to go to zero and our stock to lose all of its value.”

MIT teaches operating systems by giving students a complete Unix-like kernel and asking them to modify it. it's called xv6, a ~6,000-line reimplementation inspired by Unix V6. processes, system calls, virtual memory, and filesystems are all there