Yeah this has been my experience too. LLMs don’t handle project specific code styles too well either. Or when there are several ways of doing things.

Actually, earlier today I was asking a mixtral 8x7b about some bash ideas. I kept getting suggestions to use find and sed commands which I find unreadable and inflexible for my evolving scripts. They are fine for some specific task need, but I’ll move to Python before I want to fuss with either.

Anyways, I changed the starting prompt to something like ‘Common sense questions and answers with Richard Stallman’s AI assistant.’ The results were remarkable and interesting on many levels. From the way the answers always terminated without continuing with another question/answer, to a short footnote about the static nature of LLM learning and capabilities, along with much better quality responses in general, the LLM knew how to respond on a much higher level than normal in this specific context. I think it is the combination of Stallman’s AI background and bash scripting that are powerful momentum builders here. I tried it on a whim, but it paid dividends and is a keeper of a prompting strategy.

Overall, the way my scripts are collecting relationships in the source code would probably result in a productive chunking strategy for a RAG agent. I don’t think an AI would be good at what I’m doing at this stage, but it could use that info. It might even be possible to integrate the scripts as a pseudo database in the LLM model loader code for further prompting.

Impressively intelligent image choice and subject angle for the present psychological tug

deleted by creator

Yes .docx.

It appears as though the encoding is missing in such a way that nothing in Linux recognizes the file. The underlying CLI tools don’t have a way of converting the file. I tried with Python’s docx tool and with iconv. It has to be encoding related because some tools initially load the file with several sets of Asian characters instead of English. However, there is no hexadecimal or sections of entirely binary looking data. Archiving tools do not open up the the file to reveal anything else like a metafile or header. Neo vim shows garbled nonsense throughout. Bat warns of binary. Python won’t load the file, nor will Only Office. Libre Office and Abi Word load initially with Asian characters before crashing.

The only option is likely gong to be setting up the W10 machine and converting a bunch of files within it.

Ultimately, my old man thinks he can be an author all of the sudden and is trying to write. He’s not very capable of learning. I’m not confident that he can learn to use FOSS to do the same thing he has been doing. This post was just to see if there are options I am not already aware of that might actually work in practice. I can easily do everything I need in FOSS. I can do everything he needs to do. I’m more concerned about becoming his tech support when he forgets how to copy pasta. He already fails to separate the internet hardware connectivity from the web browser and operating system within his mental model of technology.

All of the office suites seem to use either Python 3 docx or iconvert under the surface. These tools do not support whatever default encoding m$ is using. It is clearly a font encoding issue, but I won’t know what that font is until my back is in good enough shape to setup a desktop at my bedside workstation.

deleted by creator

deleted by creator

deleted by creator

deleted by creator

deleted by creator

Too many documents and Office 365 is a $10 month sub scam.

Distilbert https://huggingface.co/distilbert/distilroberta-base

…was setup for something like that here but note that the repo that runs this has an “unsafe” warning that I have not looked into: https://huggingface.co/spaces/nasrin2023ripa/multilabel-book-genre-classifier

https://huggingface.co/spaces/nasrin2023ripa/multilabel-book-genre-classifier/tree/main

It might be fine or whatnot, I’m on mobile and can’t see the file in question. The associated Python code might be a helpful starting point.

In my experience, most models intentionally obfuscate copyright sources. They all know the materials to various degrees, but they are not intended to replicate sources. They all have strong interference in place to obscure both their recognition and reproduction potential. If, for instance, you can identify where errors are inserted and make a few corrections, they often continue adding a few details that are from the original source. If this is done a few times in a row, they tend to gain more freedom before reverting to obfuscation again. This is the behavior I look out for. It is a strong tool too if you get creative in application.

Perhaps someone posts an API to look up the library of congress classification of a work based on a few lines or something. GL

There are likely automatic checks in the startup script. I don’t use A1111 any more in favor of Comfy and I only have a 3080Ti with 16 GB (mobile version). I can run within issues. The only time I have issues with anything AI related is when I need Nvidia’s proprietary compiler nvcc. I need nvcc to hack around with things like llama.cpp. With nvcc, it can have issues with the open source driver

Crazy, out of the box abstract thinking here, but explosives are just highly volatile chemistry. Batteries are all about galvanic potential in slightly less volatile chemistry. Batteries were developed for life cycle reuse. For drones, surely some chemist out there can think of a way to make a single use battery that is also an explosive. Perhaps one that has the structure to mount a small electronics kit with a few motors.

I am an intuitive thinker that functions in abstract thought. I am not autistic. I have had extensive testing related to my physical disability and massive head injury. You lack a nuanced understanding of the context and scope of what I am asking and why. Everyone has a limited amount of information that they can process at any point in time. For most people they can only handle around a thousand lines of code at a time. There is a major metal challenge to overcome for a person to handle a project with hundreds of thousands of lines of code. This is largely an organizational challenge. When such a systemic challenge is encountered, larger groups of people tend to come up with better solutions over time. I am limited in my exposure to other people. However, I am aware that many people here are more experienced than myself in this area. This post was an attempt at exploring different forms of organization. I’m also exploring the curiosity I intuitively pick up on that indicates many of the best programmers likely have perfect recall, or at least have a larger human byte than average. I am far more self aware than the average person, and have made the assumption that most people that are gifted in their ability to handle more information than the average person will also be self aware to a similar extent. Abstracted intuitive thinking is a rarer form of functional thought, but it is not autistic. I can apply this kind of abstraction and mobility across subjects to anything. I do conflict with personalities that lack value for intuitive thinking and abstraction, but it is because they can not see the bigger picture, their own internal conflict, and address it effectively. They also tend to see my thought process as arrogant and assumptive, but it is because they lack a contextual understanding of my real flexibility and mobility across abstracted subjects and ideas. For example, when you hear the stories about Einstein abstracting the light from a train to extrapolate the principals of the speed of light, or a man falling from a roof to abstract the properties of gravity, that is a very familiar way of thinking in my mind. Everything I encounter is like this; where I am fitting the pieces together and noticing connections and coincidence that I find amusing. I’m very aware of the assumptive bases and correcting it constantly. I operate on the statistical probability of my assumptions, but I use all mental spaces to support each hypothesis and remain open to any new information that better fits what I already know.

This is all I see as lead mod of 3d printing. I also checked and desktop is the same both in desktop mobile view and on my laptop.

Human byte was used in a conference awhile back to refer to the amount of information one can process at any given point in time. Someone that has total recall has a much larger human byte. The term makes clear intuitive sense to me, but I’m a highly abstracted person in the first place. My abstraction seems to limit how much complexity I can manage with a project and code. I’m largely exploring the implications and contrasting personalities to better understand how people are able to manage so many details in some projects.

I’m messing around with trying to understand the game Cataclysm DDA at the moment, and reading into everything that is happening as it is scattered all over the project is a struggle. When I see all the pull requests and the daily release cycle of the game, I’m baffled by the way someone is able to manage this kind of project and maintain an overall vision and consistency in the game and code. I feel like I must be missing some critical element of methodology.

I exist in a vacuum, and live under a rock. I was an advanced fabricator, got disabled, and now largely stuck finding myself while exploring the digital world. I’m learning entirely on my own and without any background or mentors. In abstract, I might spend forever trying to invent the wheel if I fail to ask the right questions.

I would rather vote identities being blocked from scraping. I don’t care about other users or admins. I would rather that level of information be unavailable to outside commercial sources, especially any timings based metadata that could be used to derive dwell time and other psychological metrics.

I’m asking to find out if there is a class and if it has a goto book, but leaving it open ended for other techniques like maybe Emacs and the org mode stuff, etc.

(I’m hacking around with Cataclysm Dark Days Ahead at the moment) Noooooo!!!