I’ve made an LLM-driven web browser. I’ve named it Zenbot. It’s just a mathematical word-generator with a set of word-tools, let loose on the internet. It’s sort of built to translate commands into actions, directly, using the Python coding language, which I’ve noticed is basically English.
I’ve described it like this: “Synchronous communication becomes asynchronous communication in an elegant double-helix of English language-powered Python interpretation driven by you, the user.” as I noticed two types of Python functions, sync and async, could be utilised together when an LLM was involved in the mix.
It’s sort of like if a whole restaurant shared one brain, which was passed from customer to waiter to kitchen and back again, and at the end of the chain a customer has their order. If you ask Zenbot to ‘search for pizza’, it will search for pizza.
There are, of course, lots of advantages to doing it this way, which I focused on, like:
Efficiency
Speed
Capability
Versatility
Security
As I don’t use any traditional method. I believe the LLM should be modelled on the task, not vice-versa.
I am of the opinion that Zenbot demonstrates how mainstream approaches to LLMs are changing. Small, tailored models are the future for operating untold new and old technologies. I still do not know if they should be writing words that mean things to humans. But it’s a brave new world!
I’ve got lots more ideas for projects, and Zenbot is getting some improvements as we speak. likecommentsubscribe
Pretty proud of this one. AI slop does have a purpose, if used effectively, and in consideration of its limitations. I guess it’s a medium, and one that equalises the availability of resources for anyone.
If anyone’s willing to invest, I’d set up a studio and produce all kinds of wild shit.
Well’s Rest is available once again. Purchase it now from your local Amazon retailer. I know, I know, it has been released before in unfinished states. I’m totally okay with that. I’ve always, one-hundred percent, absolutely known exactly what Well’s Rest is and what it would look like when it was done. It is now how I imagined it to be.
So what is it?
Well’s Rest is a dark, cursed gem of mysterious origin. Its watery facets are polished and gleaming. If you hold it the wrong way it may cut you. You may be tricked by the folds of light within its angles into staring at it for far too long, consumed in mind by a strange, mad energy. You may laugh, you may scream, you may fight back, but the flowing shapes of the Obotema unfold unbidden across the landscape of your imagination and drag you into the depths of its terrible beauty.
Well’s Rest is, obviously, a metamodern western set on the sea. It is grimdark, it is horror, it is action/adventure. It’s a post-apocalyptic pirate story à la Mad Max crossed with Pirates of the Caribbean. It is also a bit H.P. Lovecraft. If it were a musical genre I would say it fits in with the likes of Alestorm or Mastodon, but with a bit more psych prog flair. It is also erotica. You can find it in that section of Amazon. Yes, I did that on purpose.
I also published it unfinished on purpose. Part of it is like a Breaking the Magician’s Code type thing. I enjoy showing people the workings of my books. I think it goes to show that the processes that go into creating art are notably abstract, with intent and inspiration sometimes hard to pin down. I, for instance, don’t necessarily identify as any particular character or another, and nor should anyone else believe they are fully represented by my work. It wouldn’t be honest or fair to suggest the author wants the same thing the main character does. The author’s views may not even be represented by the art at all. It is an arcane process of subtle delineation, and sometimes changing the orientation of those separated pieces reflects more outwardly, away from the author.
The other part of it is the redemption arc of it all. The part that reminds people that if you stick with things you are able to improve your skills and get better. I know that Well’s Rest is a great book. I know this because I know how shit it has been, and how far it has come. I am proud of this book. I have always believed in it. I knew it had what it took, always. However, the response towards both the book and myself that I have had in my life has been mixed. It has been eye-opening, disappointing, and bittersweet. There are few real friends in foxholes.
Still, I have seen support. I appreciate it.
Anyway I’m making a book trailer out of AI slop. I found one that lets me do violence. Here’s a teaser:
Fucking sick, right? I’ve got DOZENS of these. Most of them are pretty bad. Still.
Another complete disclaimer about AI. AI is an advanced Ctrl + F. I completely ignore all of its technical corrections outside basic usage cases (captain vs. Captain, for example). I do not like using em dashes and semicolons for everything. AI gives its lower-order grammatical suggestions and I apply higher-order thinking and do a better job. It’s as simple as that. I love syntax, but for me it is the last step in the process, and the fiddliest. Also, when dealing with thematics, imagery, symbolism, breaking down any concept at all, narrative structure, pacing etc., y’know, storytelling, that’s my job. My heart is fine, I do not need a pacemaker.
Okay, thank you! Buy my book. If you’d like to read a sample of my upcoming work please head over to the Writing tab.
LLMs represent something I’ve wanted to do since I was about nineteen years old, when I first published Rolling Sixes. There was a thing I was reading about called Natural Language Processing. For more information about Natural Language Processing, ask your AI. It’s what your AI was built on. Its function is using computers to interpret language. It’s computer-assisted linguistics.
Linguistics deals with the study of language, mostly words, because words help us interpret the world around us. With NLP, AI does a very good job of building a cunning edifice of words around the concepts and ideas that make up our world. It doesn’t understand these things. It only builds, its constructions based on mostly statistical methods. LLMs model ideas, but won’t always give an accurate representation of those ideas. People can be dumb in the same way. Words, or the way we interpret them, give us a similar intellectual condition. I’ve had trouble writing this piece because I feel like many are already aware of the confusing nature of rhetoric, but still, many seem to treat the capacity of LLMs as some omniscient Ask Jeeves regardless. AI’s use of language does much to expose the fundamental flaws in our basic comprehension of the world around us. I love to see it.
But that’s beside the point. Natural Language Processing can detect deliberate rhythmic structures of language at a glance and that is a beautiful thing. It’s exactly what I’ve always wanted. Of course there are issues, like how it needs different questioning tactics and a lot of coaching to get a decent picture out of it, but it works.
It’s a massive achievement in technology overall. I think it’s fucking sick that you can directly build images and video out of language now. I can direct my imagination into Veo3 and have something come onscreen in seconds, which is magic. There’s an argument to be made that written prose skips the whole ‘screen’ aspect, but that’s a whole different discussion.
I also think it’s fucking sick that I can now do what I wanted to do when I was nineteen and model, chart, and graph the absolute shit out of my books. I can get full quantitative analyses of my prose, breaking down the syntactic structures I used to build it. I can find out what percentage of my sentences were short vs. long, for example. I can find out how many adverbs I used. I can break down and model the grammatical conventions of a sentence like a decision tree. When I was nineteen I tried to do exactly this for Rolling Sixes, a book you shouldn’t bother reading, by the way. I tried to install some sort of NLP processing thing on my computer but made an absolute mess of it. This was on Linux, there were probably dependencies or something, I don’t know. This was over ten years ago.
Ultimately, I don’t think if I had got it working it would have yielded anything useful besides novelty and perspective. NLP as a field is so much further than that now. Now I can get deep on the juicy stuff, like morphology (fun), and use my own work to learn more about linguistics. This is exactly what I wanted to do.
Hopefully soon I can share some of this information, but to be honest I’m not certain of the veracity of any of it. I’m working to get confirmation, as everyone should when getting results from AI.