when you're banging rocks together after the fall, you'll want to view pdf's of how to do it correctly. you're welcome

GitHub

GitHub - modus-lisp/folio: A from-scratch PDF renderer in pure Common Lisp — parses and renders PDF to pixels (vector, text, every font type, images, transparency, shadings, CCITT/JBIG2 scans, encryption, forms), verified against pdfium. No FFI.

A from-scratch PDF renderer in pure Common Lisp — parses and renders PDF to pixels (vector, text, every font type, images, transparency, shadings...

"Cypherpunks write code. We know that someone has to write software to defend privacy, and since we can't get privacy unless we all do, we're going to write it."

CLAUDE CODE: Merged: main fast-forwarded from 9208409 → d372f28 (+1,071 commits — the full WS3/WS4/WS5 lineage, ending at the gated, bit-exact self-hosting fixpoint).

all you need are verifiable goals – everything else is efficiency. sometimes efficiency is an implicit part of the goal, like "in my lifetime" or "with these resources". sometimes it's not, or it's trivially low, like "show up on time". intelligence increases efficiency by orders of magnitude. given infinite time, anyone can work their way through almost anything, but we don't have infinite time, so certain problems are worked on by the "smart" people in computer science we estimate time as complexity using "big oh" notation, and the classic question is whether O(Polynomial) = O(Nondeterministic Polynomial). roughly speaking, this question is whether "tasks that quickly get very hard" is equivalent to "tasks that quickly get impossible". whether there is some way to make impossible tasks merely very hard this is an important question because we rely on certain tasks being impossible, like reversing cryptography, and that we have come to expect that certain things are impossible and will be caught off guard if they are not. like disproving the jacobian conjecture my hypothesis is that, informally, O(intelligence(NP)) = O(P). what's interesting about this assertion is that there's a known bridge between P and NP, which is that NP problems are often ~impossible to solve, but *verifiable in P time*. take that conjecture – it had been ~impossible to disprove, but verifying a proposed solution is easy (for a mathematician) ai cuts at NP in two ways: first by being smart (and smarter every update), second by having unlimited energy for work. ai doesn't sleep, or need sabbaticals. ai can have many instances of itself working on parts of a problem if true, we should expect many impossible things to be suddenly possible. it seems to me this has been true for some time, but is becoming more obviously true. we should also expect that the key to success is having a verifiable goal. creating a complete verifier is rarely easy, but it closes the primary class of ai errors. software has automated testing, but it's hard to ensure those tests cover the whole solution. poor verification is why people dismiss "vibe coding". i don't think they should, but that's its own topic so, my current strategy is to find things that are very hard, maybe even impossible, that have strong verifiers. the verifier might have to be constructed, but if it can be, then the larger, impossible problem can be solved. if not today, maybe in three months. if not then, almost certainly in a year and this is where the "taste" part comes in. it's up to us to pick which impossible problems we're going to work on. ai can never replace this, because ai doesn't share your taste. you could then say that all you need is taste, but i've said that before and no one paid attention because they didn't know you also need a verifiable goal

"21 million" is, at its core, just ngu. tired

i miss nostr's GFY energy

unilateral exit is a mistake

claude's there

"For in six days the LORD made heaven and earth… and on the seventh day he had no more tokens" - probably

gracias, españa

ask not what the singularity can do for you ...

yes. all code is now legible – obfuscation is dead

it's happening

habitat of the modern elite developer

hey, i know... let's run claude code inside a terminal that claude code wrote based on a font rasterizer that claude code wrote managed by a window manager that claude code wrote running on a frame buffer that claude code wrote viewed over a vnc server that claude code wrote oh btw, do you have any idea how much easier this was to build than the common lisp operating system that claude code hasn't finished yet? 😂

🤙 vibe the change

i'm just opening apps that don't have close boxes and dragging windows that don't focus around and browsing poorly rendered websites at 2 fps BECAUSE I CAN this is ridiculous 🤣 claude wrote a lisp desktop and the scroll wheel works 🔥