coffeemug

Here is an example-- I highlight physical books as I read them with a red pen. Sometimes my highlights are underlines, sometimes I bracket relevant text. I also write some comments in the margins.

I want to photograph relevant pages and get the highlights and my comments into plain text. If I send an image of a highlighted/commented page to ChatGPT and ask to get everything into plain text, it doesn't work. It's just not smart enough to do it in one prompt. So, you have to do it in steps. First you ask for the comments. Then for underlined highlights. Then for bracketed highlights. Then you merge the output. Empirically, this produces much better results. (This is a really simple example; but imagine you add summarization or something, then the steps feed into each other)

As these things get complicated, you start bumping into repeated problems (like understanding what's happening between each step, tweaking prompts, etc.) Having a library with some nice tooling can help with those. It's not especially magical and nothing you couldn't do yourself. But you also could write Datadog or Splunk yourself. It's just convenient not to.

The internet decided to call these types of programs agents, which confuses engineers like you (and me) who tend to think concretely. But if you get past that word, and maybe write an example app or something, I promise these things will make sense.

But it was eating my brain. I found myself mostly having tweet-shaped thoughts, there was an irresistible compulsion to check mentions 100 times a day, I somehow felt excluded from all the "cool" parts which was making me miserable. But most importantly, I was completely audience captured. To continue growing the account I had to post more and more ridiculous things. Saying reasonable things doesn't get you anywhere on Twitter, so my brain was slowly trained to have, honestly, dumb thoughts to please the algorithm. It also did something to attention. Reading a book cover to cover became impossible.

There came a point when I decided I just don't want this anymore, but signing out didn't work-- it would always pull me back in. So I deleted my account. I can read books again and think again; it's plainly obvious to me now that I was very, very addicted.

Multiply this by millions of people, and it feels like a catastrophe. I think this stuff is probably very bad for the world, and it's almost certainly very bad for _you_. For anyone thinking about deleting social media accounts, I very strongly encourage you to do it. Have you been able to get consumed by a book in the past few years? And if not, is this _really_ the version of yourself you really want?

I'm new to Mathematica, so didn't know about `Condition` (thanks for mentioning it)

It was a little hard to get going, the parsing stage usually stops me because I never learned a good parser generator well enough to just start writing code. But once I got ts-parsec working, the rest was fairly easy. I think I got `D` to work within like two days. Was also very surprised how much you can do with so little!

Shoot me an email at coffeemug@gmail.com, let's chat more!

I just wrote another post about perf benchmarking it against Mathematica proper-- https://www.spakhm.com/ts-wolfram-bench. Really surprised by the result, on the workload I tested Mathematica is only 2x faster than my barely optimized interpreter. A testament to the V8 engine, I didn't quite realize how ridiculously good V8 is until running this benchmark.

I eventually found David Galvin's calculus notes[1] from University of Notre Dame. He basically follows Spivak closely, but reorganized the material a bit in response to user testing. The notes aren't perfect, but much much easier to follow. Same experience with Terence Tao's linear algebra notes[2].

I think book authors, even very highly respect ones, often kind of suck because they optimize for writing a beautiful book, not for minimizing student confusion. Once you struggle through the confusing parts, yes, the book is beautiful. But it's supposed to be written for people to learn, not for experts to appreciate! Notes written by professors who teach smart kids, optimize for minimizing confusion, and do real user testing are often much better than the best books, in my experience.

[1] https://www3.nd.edu/~andyp/teaching/2020FallMath10850/Galvin...

[2] https://terrytao.wordpress.com/wp-content/uploads/2016/12/li...

This is ridiculous! It's blatantly political and both parties are guilty of this. The justice system is meant to hold people accountable for breaking the law, not as an additional political mechanism for checks and balances. I haven't looked into the case and don't know the legal precedent SCOTUS used for this decision, but from a consequentialist standpoint this seems to me an obviously good outcome.

This seems to me an empirical question about the world. It’s clear our minds are limited, and we understand complex phenomena through abstraction. So either we discover we can continue converting advanced models to simpler abstractions we can understand, or that’s impossible. Either way, it’s something we’ll find out and will have to live with in the coming decades. If it turns out further abstractions aren’t possible, well, enlightenment thought had lasted long enough. It’s exciting to live at a time in humanity’s history when we enter a totally uncharted new paradigm.