Josh Brown (@hashbrown490) header
Josh Brown (@hashbrown490) profile picture

Co-founder of @RoamResearch

Joined May 2017
Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)Photo by Josh Brown (@hashbrown490)
Josh Brown retweeted
Real-time speech transcription is now available in Live AI for @RoamResearch : very convenient for instantly structured vocal note-taking ! Quick reminder: AI autocomplete for Roam tables was introduced in previous update.
2
3
1
9
1,565
Exactly this. We need progressive disclosure for AI responses.
I keep having this strange experience. I'll open a model response and just... stare at it for a moment. Not because I don't understand the individual words. Because every paragraph is carrying so much context that my brain instinctively starts searching for a foothold. A familiar analogy. A single thread to pull. Some place to begin unraveling the tapestry. The strange part is that this is my own project. I know the architecture. I know the history. I know why every decision was made. And yet, more and more often, my next prompt is simply: "Explain that more simply." A year ago I was asking the models for maximum depth. I wanted the answer a room full of PhDs would give each other. Now I find myself asking for something almost opposite. Not less intelligence, just less compression. Fewer ideas per paragraph. More places for a human mind to come up for air. The models aren't inventing a new language. They're speaking perfectly recognizable English. It's just that every sentence has become densely connected to every other sentence. Each paragraph feels like a compressed graph of ideas that my brain has to slowly expand back into something I can hold in working memory. Sometimes I can't tell if the models are accelerating, or if I've simply found the bandwidth limit of my own cognition. I wonder what this feels like a year from now. Maybe the scarce resource isn't intelligence. Maybe it's human comprehension.
1
2
369
updated the document mode --> fresh look 🌱 - paragraphs sit flush with the title & the page reads like prose - hover to grab the drag hand - any section can switch back to a list when you need one
4
4
27
3,737
Roamans have been running a bene gesserit op on their own future selves Roam MCP is out! Claude and ChatGPT can now directly read and write in your graph – the long game pays off
Replying to @tszzl
Bene Gesserit driven development
3
5
1
29
6,404
It's amazing how there are still people who think AI is going to "collapse" and we are going back to the way it was.
3
278
Josh Brown retweeted
The father of seven has not finished a thought in four years. he is just moving. feeding. driving. wiping. his brain is soup and his back is finished and he has no opinions about civilization he is too tired for opinions. and meanwhile civilization is growing out of him like he is dirt and he doesnt even notice because there is milk on the floor again. the childfree man has read eleven books this year about the decline of the west and he is the decline and the books are the evidence and he will understand this at fifty eight in a room that is very clean and very quiet
702
3,420
689
32,312
3,620,059
Is there any way around the scam of heartworm medicine? You pay the $100+ for a test for a prescription yearly, then $100+ yearly for overpriced ivermectin. Can I just dose ivermectin myself?
6
2
367
✨ [[Quality of Life Improvement]] Autocomplete in Roam now shows live previews of pages and blocks, emphasizes matching terms, and shows reference counts so you can gauge relevance before you even link 🔗 Ctrl-O to toggle the preview on/off
4
8
40
6,031
Josh Brown retweeted
One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.
1,716
1,043
466
20,839
2,796,113
There is a definite Heroin aspect to all of this. I don't WANT to dig into the code. I WANT to trust claude -- at least at some level. I WANT to believe that there is a way to wield the lying SOB to generate good clean applications. So give me another hit and let me feel the euphoria again, while the world collapses around me.
75
29
8
556
32,619
Josh Brown retweeted
Wake up babe there’s a Portuguese Catholic priest who mixes Gregorian chants with industrial techno house music
1,407
10,240
1,778
80,607
4,776,417
Every time we've made it easier to write software, we've ended up writing exponentially more of it. When high-level languages replaced assembly, programmers didn't write less code - they wrote orders of magnitude more, tackling problems that would have been economically impossible before. When frameworks abstracted away the plumbing, we didn't reduce our output - we built more ambitious applications. When cloud platforms eliminated infrastructure management, we didn't scale back - we spun up services for use cases that never would have justified a server room. @levie recently articulated why this pattern is about to repeat itself at a scale we haven't seen before, using Jevons Paradox as the frame. The argument resonates because it's playing out in real-time in our developer tools. The initial question everyone asks is "will this replace developers?" but just watch what actually happens. Teams that adopt these tools don't always shrink their engineering headcount - they expand their product surface area. The three-person startup that could only maintain one product now maintains four. The enterprise team that could only experiment with two approaches now tries seven. The constraint being removed isn't competence but it's the activation energy required to start something new. Think about that internal tool you've been putting off because "it would take someone two weeks and we can't spare anyone"? Now it takes three hours. That refactoring you've been deferring because the risk/reward math didn't work? The math just changed. This matters because software engineers are uniquely positioned to understand what's coming. We've seen this movie before, just in smaller domains. Every abstraction layer - from assembly to C to Python to frameworks to low-code - followed the same pattern. Each one was supposed to mean we'd need fewer developers. Each one instead enabled us to build more software. Here's the part that deserves more attention imo: the barrier being lowered isn't just about writing code faster. It's about the types of problems that become economically viable to solve with software. Think about all the internal tools that don't exist at your company. Not because no one thought of them, but because the ROI calculation never cleared the bar. The custom dashboard that would make one team 10% more efficient but would take a week to build. The data pipeline that would unlock insights but requires specialized knowledge. The integration that would smooth a workflow but touches three different systems. These aren't failing the cost-benefit analysis because the benefit is low - they're failing because the cost is high. Lower that cost by "10x", and suddenly you have an explosion of viable projects. This is exactly what's happening with AI-assisted development, and it's going to be more dramatic than previous transitions because we're making previously "impossible" work possible. The second-order effects get really interesting when you consider that every new tool creates demand for more tools. When we made it easier to build web applications, we didn't just get more web applications - we got an entire ecosystem of monitoring tools, deployment platforms, debugging tools, and testing frameworks. Each of these spawned their own ecosystems. The compounding effect is nonlinear. Now apply this logic to every domain where we're lowering the barrier to entry. Every new capability unlocked creates demand for supporting capabilities. Every workflow that becomes tractable creates demand for adjacent workflows. The surface area of what's economically viable expands in all directions. For engineers specifically, this changes the calculus of what we choose to work on. Right now, we're trained to be incredibly selective about what we build because our time is the scarce resource. But when the cost of building drops dramatically, the limiting factor becomes imagination, "taste" and judgment, not implementation capacity. The skill shifts from "what can I build given my constraints?" to "what should we build given that constraints have in some ways been evaporated?" The meta-point here is that we keep making the same prediction error. Every time we make something more efficient, we predict it will mean less of that thing. But efficiency improvements don't reduce demand - they reveal latent demand that was previously uneconomic to address. Coal. Computing. Cloud infrastructure. And now, knowledge work. The pattern is so consistent that the burden of proof should shift. Instead of asking "will AI agents reduce the need for human knowledge workers?" we should be asking "what orders of magnitude increase in knowledge work output are we about to see?" For software engineers it's the same transition we've navigated successfully several times already. The developers who thrived weren't the ones who resisted higher-level abstractions; they were the ones who used those abstractions to build more ambitious systems. The same logic applies now, just at a larger scale. The real question is whether we're prepared for a world where the bottleneck shifts from "can we build this?" to "should we build this?" That's a fundamentally different problem space, and it requires fundamentally different skills. We're about to find out what happens when the cost of knowledge work drops by an order of magnitude. History suggests we (perhaps) won't do less work - we'll discover we've been massively under-investing in knowledge work because it was too expensive to do all the things that were actually worth doing. The paradox isn't that efficiency creates abundance. The paradox is that we keep being surprised by it.
123
608
144
3,257
558,488
2-3 claude code instances is the sweet spot for my productivity. Any more and I'm producing slop, any less and I'm waiting for Claude to finish
3
432
i’m actually more tired now than pre ai, managing this parallelism is exhausting
23
8
3
366
31,622
I can't get claude code to remember that it has a background task running and that it needs to check the background task to verify the code compiles. It's in my claude.md and it should just remember that it has a task it can view. I think it might have to do with subagents not having the parent context? or maybe compaction @bcherny
1
2
263
It makes it really difficult to run autonomous agents for long when they can't test their work. Also commands like /tasks or /context should be able to run while my subagents are working
1
177
claude also uses `git -C` instead of regular git commands, I can't allow git -C because it can commit outside of the current repo. It should just prefer git commit
142
me last week: who would need to run 5-10 claude codes at once that's ridiculous me this week: I need more screens to monitor all the claudes
7
197
Interesting take on LLMs and dynamic languages. I’d always assumed Clojure was mostly at a disadvantage compared to its host languages.
Replying to @hubertlepicki
LLMs are great at working with token-efficient languages like Ruby and other dynamically-typed environments. Tool calling gives them the same testing harness, LSPs, and linters as human programmers. And they put them to great use.
2
2
263
Recently with opus 4.5 I've found it can often figure out the shape of the data we are working with purely from code, even when the function which created the object is in a separate file.
1
1
142