Man, few things have made me feel like more of a philistine than reading Moby Dick earlier this year. I read a lot, but I've never considered myself a "literature guy" and wow Moby Dick cemented that. I did finish it, but I thought it was just an awful read, absolutely boring from start to finish. About halfway through I was just skipping pages and pages and pages of filler descriptions and incomprehensible 20-page-long speeches. I absolutely hated it, among the worst books I've ever powered through to the end.
It's definitely a "me problem," obviously people who are into literature and analysis get a lot out of it. But in future I'm gonna stick to my dumb sci-fi books where people talk in comprehensible sentences and things blow up, lol.
People like what they like, so if that's not your jam I wouldn't sweat it. That said, Moby Dick is perhaps a poor example of "literature" to start on if you're not sure you like "literature", mostly from being so long. If I might recommend trying Cosmicomics by Italo Calvino, or The Cyberiad by Stanislaw Lem, as they are easy to dip in and out of are nominally "sci fi" while still laying some claim to "literature". Lem and Calvino may lead you to Borges or PKD or Ursula K LeGuin or China Mieville - more genre artists that arguably aspire to being more than pulp.
I definitely get it not being everyone's thing. But I really really love Moby Dick. It is so funny! My wife kind of prepped me for viewing a lot of it as comedy or humor, especially toward the beginning, and viewing it through that lens absolutely helped. The language is old enough that you sometimes have to realize that the author is being funny, but it is there. I really loved all of the information about whales... that is just not true. Wasn't even thought to be true at the time.
The promotion of "classic" literature is largely about exposing you to depictions of the lived experiences of others through history. You can probably find better sources for that these days. It doesn't have to be unbearable without going into it with a specific goal (like wading into muck to save a puppy), but it often is.
I pretend to have a modicum of taste and while I didn't find it boring on the whole, there's a much smaller yet better novel that could be extracted from it. It's just way too self-indulgent and meandering at times.
So would you want a genius figuring out how to do everything you ask it to from scratch, or do you want to train someone how you want something done, so they do it the same way every time and you don’t have to explain yourself over and over?
Nondeterminism is actually a bug in many cases, and training, process and procedure, is how we mitigate it in humans.
You know what they call doing a task the same way every time? Micromanagement. Red tape. Waterfall design. In general, a bad thing. Kills creativity, slows everything down, minor setbacks become huge problems because there's no flexibility.
Defining every single step of every single task and making them perfectly repeatable works in an assembly line. But as an office assistant - and doubly so as a personal assistant - it creates inefficiency, makes dealing with edge cases very painful, and greatly increases maintenance burden of keeping all procedures up to date. Instead, giving people some leeway in how they approach their tasks and deliberately underspecifying processes to let them exercise their judgement is shown to work much better. Surely you had it covered in your training materials?
The harness that connects to a chatbot, API or voice interaction is the place to route requests to different systems. If you remember the early days of ChatGPT it explicitly said it was routing image generation to Dall-E after embellishing your request itself first.
Determining which tool to use should be a lightweight operation but I’m not expert enough to understand exactly how much lighter than a full LLM call just to recognize it needs a different tool or model.
For sure, I just know it’s tempting given the power of large transformers to throw things at an existing model.
For instance, OCR is something that can be done locally with no access to a GPU but people (including me) still often use cloud hosted multi-modal large language models for it.
In a way if people can’t yet use spreadsheets correctly (but they think they do) then it’s impossible to move them away.
Also the OP has much about the programmatic components, but Excel is also an interface. The front end of an unofficial corporate app. And people know (they think) how to use it.
I just listened to a demo of an insurance industry SaaS that isn’t yet public. Goal to move many things out of spreadsheets. Had AI agents built in and all sorts of bells and whistles. But the screens were chaos. I immediately thought it was just too “complicated” to switch a person off the busy/messy system they know - Excel.
My cynical mind think link you but also comes to the opposite conclusion.
Everyone will be writing apps.
Almost every app will be as janky as possible and people will just take the jank as the normal thing and get used to it and working around it, just like they did when every company started using electron and fake mobile apps that are wrapped buggy webpages.
With fast updates that changes every feature across updates, breaking everything and people accepting as the norm.
It's already happening:
- you can see Show HN post making it to the front page full vibecoded with as much jank as possible and the all the comments praising it and not questionning all the jank.
- I've seen it in some popular open source projects when after updates existing feature started to break constantly. The whole thing is ai coded up to the handling of bug reports and feature request and have Claude as co-commiter. I've looked in the internet to see the perception no one is complaining about it
- same at work, managers accepting slop AI solutions that are wrong at so many levels simply because it's fast and complain about the symptoms months down the line without questionning the AI part.
He made an animated button gif that scrolls the entire text of Moby Dick.
4.2 Mb, 19 hours long.
Top quality useless proof of concept. 10/10.
reply