shiptoaster

i wrote an essay about this a few weeks ago but was going to save releasing for a bit. seems like a good time to do it now noumena.com/essays/the-eng…

A junior dev asked the staff engineer: "How do I know if the AI's code is correct?" The staff engineer replied: "How do you know if yours is?" The junior dev was enlightened. Prod went down.

Social Capital™️ I have never seen the plight of my generation articulated so well. This is the core issue we must solve, we must provide abundant social capital to the next generation - using the levers of politics and private industry - or humanity as we know it will end.

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads. Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

The Certifiably Insane Way to Build an AI Agent: 1. choose a category where mistake tolerance is roughly the same as it is in self-driving cars. we chose "email-based scheduling assistant." many people want this product, but they immediately fire him if he screws up an interaction with a prospect, a candidate, or a potential investor 2. you learn that the edge cases are too complex and too frequent to be solvable. ours: managing timezones for people who travel (and change travel plans) constantly. knowing when NOT to respond, when to text the customer on the side to verify something, when to follow up, which sub-calendar to use, when to bend the rules on availability, when we can schedule that one type of call during your commute but not the other type of call. sharing your availabilities without compromising your privacy. and on and on. 3. the product doesn't feel viable, but you don't want to give up. you spend hours in a hot tub in Marin with a friend who makes self-driving cars. you make a plan to do it the way they did: hold the steering wheel. you go home and build a human-in-the-loop platform and hire contractors to serve as a backstop and catch mistakes before they happen (and to help design a map of what a world-class EA would do in every weird scenario). you decide trust is the currency in your category, so it must be the thing you won't compromise on. the product must succeed at any scheduling request, no matter how complicated. 4. you instantly feel an overwhelming market pull. so you keep going, growing that team to 75 people working 24/7 to support the nonstop scheduling needs of your customers. tons of engineering time goes to scaling the human platform instead of building the product. 5. you try to raise a Series A and investors say you are insane. your gross margins are extremely negative. they believe this is a problem worth solving, but they don't believe it is as hard to solve as you say. they want AI, not humans. your competitors put "NO HUMANS IN THE LOOP" on their landing pages to call you out. you keep going. 6. you work day and night building the harness that can meet the quality standard your customers have come to expect. you create a massive synthetic gold dataset. audit it, and clean it, label it. repeat. then, experiments. fine-tuning. RL. ACE. DSPy. sub-agents. sub agents for your sub-agents. rebuild the harness. throw more tokens at the problem. 7. some weeks you make big progress. some weeks your evals climb a single basis point, but that's better than nothing. more experiments. more tokens. john coogan said the hot trend in 2026 will be dogged pursuits. that pushes you to continue the pursuit, doggedly. 8. then, one day, you realize you are scheduling thousands of meetings a day and approaching 50% autopilot with no increase in churn or complaints. you put 150 customers in a full self-driving experiment, and they use the product MORE than they were using it when they had the human backstop. you can really start to let go of the steering wheel. 9. you don't know yet if this was a hill worth climbing, but you are nonetheless stoked that you can see the top. you have created a proprietary map of what to do in a million different situations. nobody else has that map, and the models keep getting better at following maps. your plan was to bet on trust, and your product can be trusted. today was the first day Howie crossed 50% autopilot:

Levie’s Law of AI Psychosis: The farther away you are from the actual work the more confident you are that humans are no longer needed I like it

love that AI is revealing managerial effectiveness to be a moral fiction

This is how they destroyed nuclear power in Germany. And it totally worked.

What I most desire doesn’t exist on the market yet: a coding agent model, but it’s only been trained on code reviews by Eastern Europeans.

truly one of the most amazing developments in trans-Atlantic tech policy over the past 20 years is the way that Europe set out to regulate US tech giants into the ground, but only made them more dominant as a result. This Economist headline really says it.

one of the many things that's fascinating to me about this is that twitter already had a translation feature but it required a single click before. the difference between zero clicks and one click compounded over an entire social network is enormous!

Had an interesting discussion with my front-end UI developer. I was asking him why he does not use more claude code to do things faster, and I quickly built a prototype in front of him to show how it was done. He calmly asked me, "Well, if you observe here, this button does not look like the design given in Figma." I said, "It's okay, but look at how fast we quickly built it." Then he told me, "Why is it okay to be fast but wrong with AI, but with me it has to be fast and correct?" 😁

It’s actually even worse than that. *You* are probably aligned with the world that no longer exists. You can’t use pattern matching based on people around you to plan the optimal plan for the future. You have to do some deep unconventional thinking, which even at the best of times has been a tall order.

we've all been there before

Frank Herbert was on so much damn drugs the man was able to see in the future

the zirp era created a weird implicit social contract which was that if the company is healthy then jobs were safe. that contract is now gone. the replacement is closer to the old industrial logic which is that labor is a cost to be minimized at every point in the cycle & now with ai that is clearly on the table to the tune of at least 17k peeps at meta being chopped.

This would be like the funniest possible time for a big boat to get stuck sideways in the Suez Canal

Minesweeper but it's the Strait of Hormuz. sweepthestrait.com