I'm saddened to see that Barth has passed, but I'm happy to see his work get some appreciation here. Coincidentally, I am currently reading a copy of "The Sot-Weed Factor" I picked up from a used and rare book store[0] located about 15 miles from his hometown of Cambridge, MD. It is as insightful as it is hilarious. I can't recommend it and "Giles Goat-Boy" enough.
Oh man. I have been to the Unicorn bookshop several times. Very unique place, walls of books everywhere you look. The vintage Macintosh the proprietor uses to process transactions is awesome. Picked up lots of good sci-fi from there. Hope to go back someday.
I read The Sot-Weed Factor earlier this year. It's a fascinating book, very funny and playful and connected to Maryland history. But none of the postmodern experimentalism of Giles Goat-Boy.
It might not be the flashiest, but if you want to save time building a CRUD app and avoid dealing with boilerplate code, its hard to beat JHipster. It's super configurable(has its own DSL) and integrates with most services a SaaS developer would be interested in using.
My "Wow!" moment came from a similar experiment. I asked ChatGPT to create a fictional assembly language, list and explain the opcodes (apologies if I'm using incorrect terminology. I'm not a low level developer) , then write a program and explain what the program does. It wasn't perfect , and used some opcodes it didn't mention previously, but the example program and explanation were coherent.
I then wrote my own simple program in the fictional assembly language and asked ChatGPT to evaluate it. Here are the results:
tell me the number that is in R3 after this "Flux Assembly" program:
MOV 7, R1
MOV 2, R2
ADD R1, R2, R3
The number that is in R3 after this "Flux Assembly" program is 9. The program
first uses the MOV op code to move the value of 7 into the register R1, and
the value of 2 into the register R2. It then uses the ADD op code to add the
values of R1 and R2 and store the result in R3. Since 7 + 2 = 9, the value
that is stored in R3 is 9.
Pretty interesting, but most assembly languages are similar enough. How about a really wacky fictional assembly language? ChatGPT then gave me "Zany Assembly" which included the following op code:
SPAZZ: This opcode causes the processor to randomly select and execute one of
the next five instructions in the program. It has no operands and the syntax
is simply "SPAZZ."
I then tried to "run" a simple program:
what are the the contents of R1 after this Zany Assembly program is run?
SPAZZ
MOV 33, R1
MOV 8989, R1
MOV 173, R1
MOV 20, R1
MOV 8, R1
The contents of R1 after this Zany Assembly program is run are unpredictable.
The program uses the SPAZZ op code at the beginning, which causes the
processor to randomly select and execute one of the next five instructions in
the program. This means that the contents of R1 after the program is run could
be any of the values that are moved into it by the MOV op codes. It could be
33, 8989, 173, 20, or 8, depending on which instruction is selected and
executed by the SPAZZ op code.
I was impressed (and this was after it unsurprisingly failed at Conway's game of life!)
I asked ChatGPT to act as a Unix program that assists in writing novels and to output its own man page, and it just dreamt up it’s own useful flags, like -b to brainstorm, and -p to proofread off a prompt. All of them work perfectly (although they start to degrade after a lot of time)
I feel like I’m witnessing multiple industries be made obsolete.
Nick Bostrom, the author, also wrote "Superintelligence: Paths, Dangers, Strategies" [1], which HN readers may be more familiar with. If you enjoyed that book, I would highly recommend this one as well.
For the most part, everyone is terrible at estimation [0], yet in business we do it all the time and consistently fall into the same traps. I wonder how an organization would be fare if they tried a top down approach to avoid estimation (or at least treat is as dirty process it is). Would this even be possible with the way companies are run today?
For anyone interested in learning more about the ANSI art scene and BBS history in general, I highly recommend Jason Scott's documentary series "BBS The Documentary"[0]. There is a part specifically dedicated to the art scene [1]. Watching this series in my early teen years really opened my eyes to the fact that the internet subcultures I was then a part of had been around for much longer than I was aware.
It really does go back to the 1960s phone phreak subculture as well as technophile aspects of the hippie subculture. Look for old issues of the Whole Earth Catalog.
A lot of those people from the 1990s grew up and created the tech startup scene, which sometimes reminds me of hacker/warez groups in some ways.
If you're into this sort of thing, you'll like Exploding the Phone[1] which details the history of phone phreaking and Counterculture to Cyberculture [2] which is a critical look at how the Whole Earth Catalog circle interacted with the tech scene.
>using Axiom is 10X faster than writing it in selenium/puppeteer + we handle all the annoying logic you need. We're investigating a node library for this - let us know if it would be useful.
As someone who has recently started working with puppeteer, I definitely think a library to alleviate that pain would be immensely valuable.
This outputs a series of clicks and keyboard events. It doesn't handle the logic necessary for most JS-heavy web-apps.
Scraping an infinite scroll is a good example. A naive algorithm is - scroll, wait, scrape, scroll, wait, scrape...
We have a slightly more sophisticated algorithm to deal with this. Also, what happens when you encounter a page with multiple iframes?
I'm essentially talking about a library which works with higher-level abstractions than just click and type, perhaps 'ScrapeInfiniteScroll' - and similar operations.
I always hated writing e2e tests (tools like Cypress just didn't cut it for me), so I put this together a while back (it's open source, MIT licensed): https://github.com/testfront-io/testfront-devtools
See also https://www.testfront.io/ for an actual description of how it works, but don't bother signing up. I'm really bad at marketing/getting the word out, and google took forever to approve the extension so I lost interest/ran out of money. Maybe if others show interest, I'll be motivated to resume the plans I had for it.
We’re building this at Superadmin, specifically for e2e tests. We’re a little bit early but would love to collect feedback. Can we get you in as an early user?
https://en.wikipedia.org/wiki/Doomsday_argument