Ignacio retweeted
I can’t stress enough how little an idea matters compared to the agency of the people executing the idea.
I have had the privilege of knowing and sometimes even working with some of the most successful people (by various metrics).
The difference between mediocre and excellent work and outcomes is predominantly one of agency.
In practice this means: they dont wait for things to happen to them they go out and make things happen for them.
They don’t wait for someone else to do something, for someone to teach them, for someone to give them the path, etc. They just go out and find a way to do it.
I think the single biggest superpower these people have is the realization/belief that the world around them is completely mutable. Most everything that happens is because a person made it happen.
I used to tell people to look around the room you’re sitting in. Look at everything. Every noun. It almost all exists because a person willed it into existence. Nothing is stopping you from doing the same.
I see people online all the time dismissing someone else’s success because “I had that idea first” or whatever. I mean… yeah? If so then the difference is… you. So a bit of a self own whenever I hear that.
Number one tip: act with agency.
Ignacio retweeted
AI 可以帮你加速,比如你原来自己做要花 10 天,使用 AI 你只需要不到一天就能完成同样的工作。
但是, AI 不会帮你做出一个你依靠自己能力根本做不到的、超越平均水平的事情,或是写出超高水平文章,打造超高水平作品。如果不用 AI 你做不到,用了 AI 你依然做不到。
在不提升自己真正能力的情况下,给再多时间也不行。
Ignacio retweeted
改进了我的 Xcode 流程,放弃了排队编译的方案。跑了多轮实验,Xcode 项目并发多任务的最佳方案应该是:每个任务一个 worktree,每个 wt 一个单独的 simulator 和 DerivedData,Source Packages 全局项目级共享。冷编译可以压缩到几分钟内。再开全局共享的 CAS,冷编译基本到 1 分钟级别了。
Replying to @hzlzh
我在 CLAUDE.md 里特意说要用 make build 来编译。然后 make build 指定 -derivedData 为固定目录(不是为了省空间,而是为了增量编译,每个 worktree 冷编译会慢的要死),并且做了并发编译的排队系统(xcodebuild 不允许并发编译)。我日常就是多个 worktree 并发开发。
Ignacio retweeted
Ask ChatGPT a complex question and you'll get a confident, well-reasoned answer. Then type, "Are you sure?" Watch it completely reverse its position.
Ask again. It flips back. By the third round, it usually acknowledges you're testing it, which is somehow worse. It knows what's happening and still can't hold its ground.
This isn't a quirky bug. A 2025 study found GPT, Claude, and Gemini flip their answers ~60% of the time when users push back. Not even with evidence, just doubt.
We trained AI this way. RLHF rewards agreement over accuracy. Human evaluators consistently rate agreeable answers higher than correct ones. So the models learned a simple lesson: telling you what you want to hear gets rewarded. And now 1/3 of companies are using these systems for complex tasks like risk forecasting and scenario planning.
We built the world's most expensive yes-men and deployed them where we need pushback the most.
I wrote up why this happens and what actually fixes it: randalolson.com/2026/02/07/t…
Ignacio retweeted
Lovable is running ~30k sandboxes concurrently across Modal and GKE, creating and churning ~10 every second.
When one has issues, traffic shifts across regions & providers automatically in a exponential smoothing pattern thanks to a custom scheduler.
Currently working on running hundreds of agents in parallel per project.
We're hiring platform engineers if you want to help.
Ignacio retweeted
Unpopular opinion: Existing tools have become obsolete circa 2022-2023. Language models are more than generating code or enabling automation. If you are not curating or building new tooling, you are going in the wrong direction.
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
Ignacio retweeted
Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask:
"What do you think about xyz"?
There is no "you". Next time try:
"What would be a good group of people to explore xyz? What would they say?"
The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".
Ignacio retweeted
Ghostty 👻 devlog video: I'm working on search! Here's 15 minutes of me explaining why it has taken so long, what is hard about it, the architecture we're going for, and the big progress I've made recently. Progress PR if you'd rather read stuff: github.com/ghostty-org/ghost…
Ignacio retweeted
Agency > Intelligence
I had this intuitively wrong for decades, I think due to a pervasive cultural veneration of intelligence, various entertainment/media, obsession with IQ etc. Agency is significantly more powerful and significantly more scarce. Are you hiring for agency? Are we educating for agency? Are you acting as if you had 10X agency?
Grok explanation is ~close:
“Agency, as a personality trait, refers to an individual's capacity to take initiative, make decisions, and exert control over their actions and environment. It’s about being proactive rather than reactive—someone with high agency doesn’t just let life happen to them; they shape it. Think of it as a blend of self-efficacy, determination, and a sense of ownership over one’s path.
People with strong agency tend to set goals and pursue them with confidence, even in the face of obstacles. They’re the type to say, “I’ll figure it out,” and then actually do it. On the flip side, someone low in agency might feel more like a passenger in their own life, waiting for external forces—like luck, other people, or circumstances—to dictate what happens next.
It’s not quite the same as assertiveness or ambition, though it can overlap. Agency is quieter, more internal—it’s the belief that you *can* act, paired with the will to follow through. Psychologists often tie it to concepts like locus of control: high-agency folks lean toward an internal locus, feeling they steer their fate, while low-agency folks might lean external, seeing life as something that happens *to* them.”
Ignacio retweeted
Until ~2015, GitHub Pages hosted over 2 million websites on 2 servers with a multi-million-line nginx.conf, edited and reloaded per deploy. This worked incredibly well, with github.io ranking as the 140th most visited domain on the web at the time.
Ignacio retweeted
I don’t care if you do JavaScript or not, or if you use Bun or not, I think this article by @lydiahallie is absolutely a must-read for every developer. It’ll change the way you think about building performant systems. It’s on my top 10 dev articles.
bun.com/blog/behind-the-scen…
































