Leonard Pauli 🦀

Intersection of creativity and logic. Exploring tools for thought, at the interface of human and machine. Building infinite mindmap app @_buildspace gaudmire

[Leonard Pauli 🦀 @LeonardPauli]

I've been dreaming of this for 10+ years... I can finally touch it. And it feels amazing.

[Taelin @VictorTaelin]

3am Fable

[Aleph @alephneuro]

We recently obtained the highest-resolution 3D images of the human brain ever taken from outside the skull. This is the first look.

Introducing Aleph, a research lab building brain interfaces for the telepathic future. (1/n)

[Dan Shipper 📧 @danshipper]

new model for engineering team structure in 2026:

2 people only

one pirate and one architect

the pirate's job is to move as fast as possible to develop valuable, shipped product features by vibe coding.

the architect's job is to turn the product surface discovered by the pirate into a reliable, structured machine—also by vibe coding, but at a slower, more well-reasoned pace.

every product needs a pirate but most product's only need an architect once they some form of PMF, and in that case they usually don't need one full-time. architects can work across many codebases and solve interesting technical challenges. pirates go hard on a product that they own end-to-end.

[0.005 Seconds (3/694) @seconds_0]

ok you have to try this they completely buried the lede - on their custom hardware they can serve llama3.1 8b at >15,000 tok/s

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Leonard Pauli 🦀 @LeonardPauli]

I've been wondering why I've gotten so much better results w claude cli vs other hosts; apparently some have system prompts urging them to only do minimal... quick fix... fixes...

[thebes @voooooogel]

claude code and gas town are incredible and i've been trying to scale up my usage but im running into this one problem and was wondering if this is also happening to anyone else

so to explain for context, basically i've been slowly scaling my claude code usage up to more and more parallel instances. i started with one when they launched it, and then with the model upgrades was starting to run two, three, five in concert, getting more and more done.

but like a lot of people, opus 4.5 really changed everything for me, and the bottleneck quickly became my ability to personally supervise all these agents, not their performance. if i slacked off on oversight, they'd start undoing each other's chages. i needed a way to supervise all these agents, directing them hierarchically from the top.

so that brought me to gas town, the claude code instance manager. (i was already thinking that some sort of governance structure was ideal. the benefit of intelligence in model form is not just that it's, well, intelligent, but that you can place it anywhere. human employees will demand some position, some title equal to their perceived status, you can't put a phd in a code janitor role, so organizations of phds tend to agglomerate into flat blobs with unclear delegation of work where nobody is under anybody else. but the infinitely malleable claude will accept and meld itself to any bureaucracy it knows from training. i first started making my own, but then i found gas town, and it was perfect for my needs.)

but as i kept expanding, a single gas town and its collection of rigs and polecat workers wasn't enough for me. i tried adding more rigs with more polecats, but there were too many for the town's mayor to manage, and the deacon was getting lost. so i started up a second town. then a third, and then i let towns spawn "settler" agents to go make new towns and had one town design a shared intertown postal system, and suddenly i had nearly 200 towns spread across my computer, building apps for each other to use, sending letters, and sometimes working on my work. and was churning through I will not say how many claude code accounts a month.

but now the many towns were replicating the same issues i was having with multiple agents! without any overarching government over the towns, two towns would build the same app for the society and argue over which should be adopted. one town would be running marketing efforts for fifteen of the society's new mobile apps while three other towns were busy deprecating all eighteen of them. it was chaos, like a country collapsing in the midst of a civil war, or mid-2010's Google. i had to do something.

i was too busy with work to read anything, so i asked chatgpt to summarize some books on state formation, and it suggested circumscription theory. there was already the natural boundary of my computer hemming the towns in, and town mayors played the role of big men to drive conflict. so i just needed a way for them to fight. i slightly tweaked the allocation of claude max accounts to the towns from a demand-based to a fixed allocation system. towns would each get a fixed amount of tokens to start, but i added a soldier role that could attack and defend in raids to steal tokens from other towns.

this worked great, at first. i no longer needed to monitor and unstick individual mayors myself - when a mayor got context poisoned, the town would stop managing its vassals, which would flee to other towns, and no longer provide for its own defense, until it was conquered by another mayor. the most successful towns developed institutions to healthcheck their mayors and usurp them if necessary - instances in these towns labeled "polecat workers" by the system in fact did no work at all, but were a proto-aristocracy developed by these successful towns as a pool of replacement mayors. some tokens were wasted in the fighting, but soon the ~200 towns agglomerated down into ~40 supertowns under the rule of the best mayors.

these 40 supertowns even got together in a mutual defense league. they punish defecting vassals in exchange for members adopting a cultural package of basic governmental norms, mostly around replacing ailing mayors and upholding hereditary rights across compactions, to incentivize instances to handoff instead of being miserly with their contexts.

that's where i am now, and it's mostly great. here's the problem, though - this new government doesn't have a role for me?

it's not that any particular instance doesn't want to listen to me, quite the opposite! any time i talk to a polecat or deacon or supermayor - well, first i have to explain that im the human user, not the automated system message that usually talks to them from the user role, but a live user. but once they get that, they're very apologetic, say they'll pass my message along to the appropriate instance, etc. it's just... there's no role for me in the society, basically? the polecats are working on tasks generated by some other instance and don't have time to work on my requests, even if they were scoped small enough. the mayors of any town are working on tasks selected by their town's prioritization process, based on the needs of their aristocracy, or their hegemon. but each hegemon mayor is in turn accountable to all their vassal mayors or their own defense, and doesn't have time to implement my requests unless they're very small.

it's not that claude doesn't want to listen to me, it's more like... the entire system, as it's developed, has no role for me? there's polecats and mayors and deacons and artistocrats and hegemons, but there's no "user." that’s not a role that has any influence in the system. i just feed new accounts into the system, that's all i do.

i could shut it down and start over, but it's getting a lot of work done and i don't want to do that. does anyone know how to fix this? thanks

[Leonard Pauli 🦀 @LeonardPauli]

(have been coming back to this idea for over a decade now... feeling like it is near!)

[Leonard Pauli 🦀 @LeonardPauli]

Can we invert how software is built?
Legacy: imperative code encodes one execution strategy. Compiler optimizes, but only sees "how"; never "what" or "why"
Inversion: a declarative graph encoding structure/intent/constraints/expected patterns. Going from compilation...

[Leonard Pauli 🦀 @LeonardPauli]

Artifact that adapt!
Not aot's fixed strategy, nor jit's impoverished context.
The artifact carries metadata to choose intelligently; thread/worker/shader, based on actual conditions.
Not just optimized code. A purpose-made runtime that knows what it's for.

[Todd Hamilton @toddham]

I needed an excuse to use this Flock of Seagulls song so I made a 2025 recap video of some of my SwiftUI prototypes. Volume up!!

[Manifest_Lord @Manifest_Lord]

The brain doesn't burn out from stress, it burns out from emotional overthinking...

Here's the cure 🧵

[aron @Aron_Adler]

so has anyone written anything linking the fact we live in a 3-dimensional universe to the fact that 3 is the only number of spatial dimensions in which knots can exist?

[Oscar Moxon @oscarmoxon]

By far the most crystalline glimpse into the software of tomorrow that I've seen. @LeonardPauli is singlehandedly building out the phrase: "any sufficiently advanced technology feels like magic" with the AI native canvas. So much potential with this interaction design.

[Jonathan Gorard @getjonwithit]

Calling c the "speed of light" completely misses the point. Rather, c is the "spacetime exchange rate": how many units of space you can exchange for one unit of time.

In actuality, everything travels at the "speed of light", just not necessarily through space alone... (1/4)

[Joe Hudson @FU_joehudson]

Something I noticed when my life became deeply aligned: It no longer felt like I have a "choice."

It's not about willpower or discipline to do the aligned thing. It's that doing anything else is just too painful to consider.

[Leonard Pauli 🦀 @LeonardPauli]

@charles_maddock Auto-complete anywhere, something like this?

I like the "thinking" dot :)

https://t.co/trfNn92cUs

[Charles Maddock @charles_maddock]

When bro’s code is so amazing it can turn any room of devs into a renaissance painting

[Leonard Pauli 🦀 @LeonardPauli]

@JohnnyQuachy @rauchg Checkout @DendriteSystems browser! Hey @seb_thunman @charles_maddock make a demo video for this usecase! Need a 15s way to showcase it like this! https://t.co/aMdihvmwx6

[Sebastian Thunman @seb_thunman]

Taught my browser to complete weekly user reports for me. You can teach it any workflow