Tomas Millar

@bcherny The way the development team communicates with the users... 🙂

Hope this was useful! I wanted to keep going but had to stop myself. Will post more soon. What are your favorite underrated Claude Code features?

I wanted to share a bunch of my favorite hidden and under-utilized features in Claude Code. I'll focus on the ones I use the most. Here goes.

We invited Claude users to share how they use AI, what they dream it could make possible, and what they fear it might do. Nearly 81,000 people responded in one week—the largest qualitative study of its kind. Read more: anthropic.com/features/81k-i…

There’s a fundamental difference between taking an existing process and applying AI agents to it vs. taking a process from scratch and designing it from the ground up for AI agents. The gap we’re going to see will widen between the teams and companies that are able to do the latter instead of just the former. In theory it would have been ideal for all the gains of AI to have come “for free”, but there are both clear constraints of AI (like getting the context right) and clear upsides (like being able to execute code and run in parallel) that the workflows themselves must be redesigned to take full advantage of this technology. One of the biggest implications that will come into focus is that agents that can write and run code, and interact with any API, will lead to agents effectively being expert engineers applied to your business process. So to some extent one of the biggest ways of reengineering a workflow is to ask yourself: what would you do if you had an infinite number of capable engineers write software for this process. What if those engineers wrote code to connect your disparate data sources, comb thorough any amount of unstructured data, automate your repeated tasks, connect your various systems together specific to your process, and so on. Not every process has that upside, but there tons of tasks that we do every day across marketing, finance, operations, and even sales, where a programmer with infinite code writing and API access would be able to make something go far faster or produce way more output. The teams that start to think this way will start to operate entirely differently.

We need a name for “I really should be spending all my time talking to AI, but I’m not”. AI pre-psychosis? Or is it just AI psychosis? Asking for a, well, you know…

prediction re the end of spreadsheets AI code gen means that anything that is currently modeled as a spreadsheet is better modeled in code. You get all the advantages of software - libraries, open source, AI, all the complexity and expressiveness. think about what spreadsheets actually are: they're business logic that's trapped in a grid. Pricing models, financial forecasts, inventory trackers, marketing attribution - these are all fundamentally *programs* that we've been writing in the worst possible IDE. No version control, no testing, no modularity. Just a fragile web of cell references that breaks when someone inserts a row. The only reason spreadsheets won is that the barrier to writing real software was too high. A finance analyst could learn =VLOOKUP in an afternoon but couldn't learn Python in a month. AI code gen flips that equation completely. Now the same analyst describes what they want in plain English, and gets a real application - with a database, a UI, error handling, the works. The marginal effort to go from "spreadsheet" to "software" just collapsed to near zero. this is a massive unlock. There are ~1 billion spreadsheet users worldwide. Most of them are building janky software without realizing it. When even 10% of those use cases migrate to actual code, you get an explosion of new micro-applications that look nothing like traditional software. Internal tools that used to live in a shared Google Sheet now become real products. The "shadow IT" spreadsheet that runs half the company's operations finally gets proper infrastructure. The interesting second-order effect: the spreadsheet was the great equalizer that let non-technical people build things. AI code gen is the *next* great equalizer, but the ceiling is 100x higher. We're about to see what happens when a billion knowledge workers can build real software.

👋 Roughly, the more tokens you throw at a coding problem, the better the result is. We call this test time compute. One way to make the result even better is to use separate context windows. This is what makes subagents work, and also why one agent can cause bugs and another (using the same exact model!) can find them. In a way, it’s similar to engineers — if I cause a bug, my coworker reviewing the code might find it more reliably than I can. In the limit, agents will probably write perfect bug-free code. Until we get there, multiple uncorrelated context windows tends to be a good approach.

@SuperClawPaul @petergyang I'm an architect and 100% agree... You need to go through a complicated stage before you reach the simplicity. This can happen with a career as well as a project...

I’m a video editor by trade, and professional editors always start with a fat cut. From a fat cut we get to our refined cut, but we can’t get to the refined cut without putting “fat” on the timeline that gives us room to work, and creates decisions for us to make that wouldn’t be possible without the fat being there. I think you can apply this to a sculptor working on his creation (a little more on the nose). I think something similar is at play with code. The cost of just “doing it to begin with” might be something that hard to describe or to see - but it’s there.

I just tried /simplify in Claude Code and now it's cleaning up my spaghetti code quite well which begs the question of why isn't this just default on? The best and worst thing about Claude Code is how much you can customize it. But for beginners how would they know about this command?

@bscholl Reminds me of the story of The Bug in The Rug - open.spotify.com/track/2hp16oue…

We call it a bird’s eye view, but this is a misnomer. As a species we weren’t born to fly—we had to learn. The view from an airplane is an unmistakably human view.

4w ago I was a Claude Code skeptic. I'm not a coder. None of the use cases were relevant. I managed teams & projects, drowning in email & overdue reminders. So I tried creating tools that would help me and... holy crap. Now I'm sharing the tools I built: claudeblattman.com

@noahzweben Has anyone got notifications working with this when a task is complete or input needed? I have them turned on in the app...

Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.

@bcherny Has anyone got notifications working with this when a task is complete or input needed? I have them turned on in the app...

Have been using this daily and loving it! Tell us what you think

Anthropic are going to win...

@paulg This is what I showed my kids to explain the same thing... youtu.be/9C_HReR_McQ?si…

Something I told 13 yo: Neuroticism and imagination are closely related, if not identical. So if you're going to be imaginative you also have to be disciplined, in order to prevent bad kinds of imagination from bringing you down.

Overshoot is the fastest API for real-time vision. Literally faster than human reaction time (<200ms). Developers are using it to ship video agents in gaming, robotics, sports and security. Check out the playground: overshoot.ai Congrats @zakariaornot and Younes on the launch! ycombinator.com/launches/PQO-o…

The effective use of agents is creating one of the widest spreads in output productivity we’ve seen on a per role basis. We didn’t see this with chatbots previously. Chatbots probably sped up work by maybe 10-20% in most cases because they largely accelerate the research on a topic you would otherwise do in a few steps manually. Now, with agents, you could take the exact same engineer and easily see a 5X+ difference in the amount of useful output simply based on their choice of tools and how they’ve designed their workflows. There probably hasn’t been a period in tech or where a couple decisions and changes to your process drive this much leverage. As this continues to expand beyond coding, this will be one of the biggest shocks to the system of what work looks like in most fields. This will happen in legal, finance, life sciences, and other areas that have previously been constrained by how much information you can process or produce. Most areas of knowledge work still imagine AI as a chatbot paradigm and not yet a full agent-executing-work-for-you paradigm. But it’s coming.

This might be the first hot take on how technology tells us how to live our lives, destroying our ability to make human decisions. The technology in question is the sundial. From a 3rd century BCE Roman adaptation of a Greek play, as discussed in Kerr’s “The Ordered Day”

So I made the objects so hot they glow, which seems suboptimal, but this is all the starlink satellites currently in orbit using Universe Sandbox @UniverseSandbox

🎯 Any one of these Russian attacks on Ukrainian civilians would be front-page news around the world requiring immediate action were they committed by terrorists in Berlin or Paris or London or New York. Normalizing the intentional slaughter of innocents is horrific.

I feel like Tony Stark and Doctor Strange 🤯 This is the CADDY app, 3D CAD visualization in mixed reality, running on Meta Quest 3

A huge political earthquake in Texas tonight as Democrats flipped a State Senate seat from red to blue in a district Trump won by 17 points. Trump personally waded in — endorsing the Republican and personally urging base turnout — and was dealt a massive loss.