USA. A Mexican restaurant. We had not yet ordered anything, and the food was already arriving. Chips. Salsa. Unrequested. Free. I stopped the waiter. "We have not earned these." "They just come with the table, man." They come with the TABLE. In my land, hospitality is a debt. Every gift creates an obligation, weighed carefully, returned in the proper season with interest of feeling. Here, the gift arrives before you have even proven you can pay for dinner. This is not an appetizer. This is a declaration: we trust you. Eat. I ate with the gravity the moment deserved. And then — I must report this calmly — the basket emptied, and a new one appeared. "Did we…?" "Refill," the waiter said. "It's bottomless." Bottomless. They have wells of salsa. The supply lines of this nation are beyond anything my ancestors imagined. My friend warned me. "Don't fill up on chips, dude." Too late. I had accepted three baskets. Honor demanded each one be finished — an unfinished gift is an insult. By the time my actual food arrived, I was a ruined man. I was not hungry. I was not comfortable. I had been defeated by a courtesy. Generosity that arrives before the request cannot be repaid. It can only be survived. I know the rule now. I have made my peace with the basket. One basket. Two at the most. Who am I deceiving. There is no number of baskets I would refuse. The trust of a nation is in that salsa, and I intend to honor all of it.

At this point every CEO should be asking what their strategy is to avoid model lock-in. If it isn’t clear what Anthropic is doing, it is: - build something amazing - decide who gets to use it after you prompt it if the prompt falls into areas they deem unacceptable by their sole standard To be clear this is completely above board and legal. It’s just an idiotic risk for corporate users to bear especially as the coding models become equivalent. The business continuity risk will become more obvious as companies accidentally trip over Anthropic’s ToS and have to decide if they will subsume their business viability to them by doubling down on Anthropic models or find open source (and, btw, much cheaper) alternatives where they are in control. As stated previously, get ready to be inundated with the term “control plane” which is the natural solution to this problem. Shameless plug - this is what 8090’s been building as we expected this moment to arrive… If you’d like to learn more: 8090.ai

Feeding you dumber responses silently, on purpose, targeting you while charging you the same amount per token totally sounds like something illegal.

苹果的发布会视频中，但凡有说到 Siri 的地方，都会切掉音频中 3k、4k、5k、6kHz 频率部分，以防观看视频时附近的苹果设备激活 Siri。

I have to push back on 2 things as i think one is categorically incorrect and the other is demonstrably incorrect. 1. Debugging: Debugging is not a thing if coding is solved. You would produce correct behaviors. I don't understand how a solved problem could produce erroneous behavior. 2. Coding is the easy part: setting hardware, capacity, talking to users, product planning agreed is in fact hard, but so is coding. Example: If coding was in fact not hard then Claude Code having a flickering issue for well over 9 months, which is a purely software challenge, would have been solved almost immediately (immediately being on a shortened time scale comparatively to a human solve time scale). For more trivial applications software approximation can largely work. I also love software approximation for exploring how things should feel.

all the ai grifters next week will be selling looping skills (again) cant wait

How we improved the product experience using @linear Agent in Slack, Coding Agent, and Diffs. A story in three acts 🧵

You might believe you should spend less time thinking about code because of AI. I strongly disagree! We’re watching this play out live where tons of AI generated code becomes a liability. At the end of the day, an engineer needs to be responsible / on call for code that gets shipped to production. If you don’t understand the system you’re trying to debug, you’re probably going to have a bad time. Yes, AI can help with all of this, if you set up the proper systems. You can have agents triage prod logs, look at errors, etc. You can speed up parts of the investigation, but an engineer needs to make the call. There might be serious customer or financial implications from that change. I expect the trend continue for trimming dependencies, vendoring code so you can modify it directly, preferring simpler systems with fewer abstractions, and spending waaaay more time thinking about system design and code maintenance. I’ve said this before, but it’s a great time to get familiar with CS fundamentals and some of the history behind what great software looks like. Many parts will be different in the coming years as AI progresses, but also a lot more than people realize will stay the same.

software engineering is solved btw

Cursor is making a platform play. Right now they're an IDE. By releasing the SDK, they're turning their agent runtime into programmable infrastructure that runs headlessly in CI/CD pipelines, internal tools, and even third-party products. Every agent spun up through the SDK burns tokens on Cursor's billing. That means revenue scales with compute, not seats, and without a human in the loop, volume can go way higher. Smart move!

Race to the bottom, inference for the same level of work goes down over time. Insane token prices à la opus, will be hard to justify and will likely be reserved for very specific tasks like running security audits, where you absolutely need SoTA.

We recently shipped Shopify Design. 

 Here's a technical breakdown of how I built it. 🧵

Quick ui.sh demo — generating multiple design ideas to choose from, no matter what tech stack you use:

Hey, I'm open-sourcing Clicky. Go forth into the wild and build the future of education and the future of AI interfaces, my friends. I'm happy to have given a spark. Enjoy! github.com/farzaa/clicky

I built this thing called Clicky. It's an AI teacher that lives as a buddy next to your cursor. It can see your screen, talk to you, and even point at stuff, kinda like having a real teacher next to you. I've been using it the past few days to learn Davinci Resolve, 10/10.

the guy keeps saying "you can already do this with a canvas behind the element" so here is another gratuitous animation where the scanline physically distorts the form content as it passes (warping the actual rendered HTML pixels)