SmokeyDope @ Smokeydope @lemmy.world

Posts

54

Comments

984

Joined

2 yr. ago

Moderating

---

You can tell because of checks notes "ThE ThIcK LInES AnD Off ColoURinG"

Thanks for the input! I do eventually plan on making some scripts and a custom web interface to interact with/expose some local services on my network once I have the basics of HTML covered as part of a portfolio thing so would like to cover my ass early and not have problems later

The thing is that even if there isn't much energy in plastic to be extracted, theres still enough energy in it to make a viable food source. Now, consider the humble koala and its primary food source, fucking eucalyptus leaves. Eucalytis is such a dogshit food source that koalas had to spend evolutionary time and energy just to spec into it. To the point they cant eat anything else pretty much. Combine that with the fact that eucalyptis leaves are so devoid of nutrients that the koala has to spend all day every day just snacking on them to not die of malnutrition.

Why? Why would a species even bother with this flim-flam if eucalypti sucks that bad as a food source? The answer is: Food scarcity. Because eucalytis grows everywhere where koalas live and because nobody else is bothering to tap into the food source, this sets up a ecological niche by pretty much gaurenteeing any animal that sucessfully finds a way to make it work will have unlimited amounts of food/energy just from the fact theres so damn much of it and nothing else wants to/can touch it. Sure koalas might have paid the price by sacrificing some brain wrinkles but who needs higher intelligence when you have leaves to snack on and sex to make babies.

A similar thing happened with trees and mushrooms. In the deep evolutionary history of our planet trees were once the apex forms of life with forest covering pretty much the whole planet. This is because nothing knew how to eat the wood stems for a good couple million years. Most of the coal and oil that we dig up today is actually the preserved remains of these unbroken down trees from the carboniferous period that just layed there petrified never rotting until the earths techtonic movement buried the tree corpses deep enough in the mantle for the carbon to compress into hard rock or squeezed+heated into liquid. The great change in the era happened when our humble mycelium bois finally figured out how to eat wood, causing them to essentially become the new apex life for a time by taking advantage of an unlimited and untapped food source (trees).

I suppose my point is to not underestimate the willingness of life to find new food sources. microorganisms don't need much excuse just a slight amount of selective pressure and a couple million/billion/trillion generations of evolutionary trial and error. Which for bacteria takes maybe a couple of years I forget how quick modern microorganism colonies make new generations but its FAST. Add some science nerds who love to play God/intelligent evolution with CRISPR tek and gene tagging, yeah for sure well get plastic eating microbes figured out. Then begins the pandoras box of plastic rotting when we dont want it to.

Havent heard of this one before now. It will be interesting to see how it actually performs. I didnt see what license the models will be released under hope its a more permissive one like apache. Their marketing should try cooking up a catchy name thats easy to remember. It seems they're a native western language company so also hope it doesnt have too much random Chinese characters like qwen does sometimes

Ive never really gotten into MoE models, people say you can get great performance gains with clever partial offloading strategy between various experts. Maybe one of these days!

If your running into the issue of an app wanting an api key for your local ollamas openai-compatable web interface API and refuses to work without one, I found that any random characters work. If you port forward your host computer you should be able to access the webui interface on an external network using the public IP.

Heres the dead simple python program I used to send and recieve text to kobold.cpp engine through the web API. Not sure how similar ollama but afaik openai-compatable API means it all should works close to the same for compatibility(I think? lol!) if you give it a shot Make sure to set the .py file you make as executable and run it from a terminal doing ./filename.py to see the output in real time. It should make a log text file in same dir as the program too. Just use your host computers local ip if the python script pc is on same network.

What is this post even talking about why does your silverware have a pillow

Just wondering, why do you think that coke users stay away from psychadelics and vice versa?

VSCode + roo plugin seems to be all the hotness for coders leveraging 'agenic teams' so I spent a bit playing around with it. Most local models dont do tool calling very well I need to see if devstral works better without giving errors. I hear real professionals use claude API for that kind of stuff.

Im only vaguely familiar with getting computers to send, recieve, and manipulate data with eachother on a local network so got a very basic python script going pointed at kobold cpps openai-compatable API to send prompts and recieve repliesinstead of the default webui app just to learn how it works under the hood.

One of my next projects will be creating a extremely simple web based UI for my ereaders basic web browser to connect to. kobold has something similar with the /noscript subpage but even that is too much for my kobo reader. I intend to somehow leverage a gemtext to html proxy like ducking or newswaffle to make the page rendering output dead simple.

One of these days im going to get a pi zero and attach it to a relay and see if I can get a model to send a signal to turn a light on and off. Those home automation people with the smart houses that integrate llms into things look soo cool

Plot twist: she knew and didn't care. "Its a doggish canine social enough to accepts the pets, a couple rabies shots and its good enough for me."

"The Grey" is the first thing to pop into my head.

The stupid meme worthy part is the way wolves are presented as a threat in the movie is so over the top like old childrens folklore level omnipresent coked out superwolves with a 100 mile killing radius stripping the territory all threatening life larger than a squrrel and enough intelligence for tactical strategizing to pick an entire group of men 1 by 1.

The way everything else is executed is what turns it around. The cinematography and the emotional human story of the main character guys motivations and interactions with the res5 of the group is fun. It makes it a good watch to spend an hour or two of your life on. The cast has some bangers and the acting is great.

Nothing wrong with a little bit of projection every now and then. It seems some people take it too far as a coping mechanism sometimes taking it to unhinged/unsafe degrees.

I consider it an ethical and moral responsibility to hide the darker aspects of my life from other people in general unless they are closely loved family or get paid to deal with such things as a career. If were just weekend night game buddies theres no reason you should be able to guess anything about my shitty life or internal suffering through poorly veiled character back story allusions. Its not your responsibility, its more personal that most are casually comfortable with, and its wrong for me to try to burden you with knowledge like that.

Revealing your deep traumas / "venting" to other regular people who only know you as a friend or passing aquanitence simply adds onto their psychological burden and likely makes further interaction weird or even secretly unwanted by complicating the relationship. Likely without improving your emotional situation any long term.

The installed appification of everything riddled with trackers when a web browser + site will do. Dead simple minimalistic UI that a toddler can figure out how to use. Every product is designed to account for the lowest common denominators of human intelligence which encourages 'cant, wont, dont know how' brain rot instead of making the tech illiterate feel pressured to actually apply themselves to learn. Now we have entire generations of idiots who feel entitled to the pleasant convince of advanced technology but unwilling to understand whats actually going on under the hood or accept responsibility to learn how to use it properly/ethically.

A society built entirely on dead simple convinence and instant gratification is one that fosters the destruction of individual critical thinking skills and mental robustness to troubleshoot/adapt when encountering a problem.

So many people are proud of it, thats the worst part for me. Legitately bragging about making it through life with the bare minimum of braincell rubbing. As if just being an unthinking half-sentient ape with a learned helplessness complex is an ideal state of being worthy of pride.

Thanks for sharing your nice project ThreeJawedChuck!

I feel like a little bit of prompt engineering would go a long way.

To explain, a models base personality tends to be aligned into the "ai chat assistant" archetype. Models are encouraged to be positive yes-men with the goal of assisting the user with goals and pleasing them with pleasantry in the process.

They do not need to be this way though. By using system prompts you may directly instruct the model to alter its personality or directly instruct it on how to structure things. In this relevant context tell it something like

"You are a dungeon master with the primary goal of weaving an interesting and coherent story in the 'dungeons and dragons' universe. Your secondary goal is ensuring game rules are generally followed correctly.

You are not a yes-man. You are dominant and in control of the situation.You may argue and challenge users as needed when negotiating game actions.

Your players want a believable and grounded setting without falling into the tropes of main character syndrome or becoming Mary Sues. Make sure that their adventures remain grounded and the world their characters live in remains largely indifferent to their existance."

This eats into a little bit of context but should change things up a little.

You may make the model more creative and outlandish or more rigid and predictable by adjusting sampler settings.

Consider finding a PDF or an epub of an old DND manual, convert to text, and put into your engines rag system so it can directly reference DND rules.

Be wary of context limits. No matter what model makers tell you, 16-32k is a reasonable limit to expect when it comes to models keeping coherent track of things. A good idea is to keep track of important information you dont want the model to forget in a text file and give it a refresher on relevant context when it starts getting a little confused about who did what.

Chain of Thought reasoning models may also give an edge when it comes to thinking deeper about the story and how its put together interaction wise. But as a downside they take some extra time and compute to think about things.

I never tried silly tavern but know its meant for roleplaying with character cards. I always recommend kobold since I know most about it but theres more than one way to do things.

Im not really into politics enough to say much about accuracy of labels. Ive been on lemmy long enough to see many arguments and debates between political people about what being 'anarchist' or 'leftist' or 'socialist' really means, writing five paragraph heated essays back and forth over what labels properly define what concepts, so on and so forth.

It seems political bias are one of those things nobody can really agree with because it boils down to semantic/linguistic arguments for redefining ultimately arbitrary drawn labels. Also arguers being somewhat emotional about it since its largely dealing with subjective beliefs, and their own societal identity politics over which groups they want to be seen/grouped based off their existing beliefs, which can cause some level of mental gymnastics.

Its a whole can of worms that is a nightmare to navigate semantically in a traditional sense, let alone try to mathematically analyze through plotting data in matrixes and extract range values. I cant imagine how much of a headache it would be to figure out a numerical chart rating 'political bias' as a 0-100 percentile number in a chart like UGI. Political minded people cant really agree on what terms really mean, so the data scientist people trying to objectively analyze this stuff for llm benchmarking get shafted when trying to figure out a concrete measurement system. The 12Axes test they use is kind of interesting to read through in itself

From what Ive seen in arguments about this, Plex generally is more accessible with QoL and easier to understand interface for non-techie people to share with family/friends. Something thats hard for nerdy people to understand is that average people are perfectly fine paying for digital goods and services. An older well off normie has far more money than sense and will happily pay premiums just to not have to rub two braincells together with setup or for a nicer quality of experience. If you figure out how to make a very useful plug-an-play service that works without the end user of average intelligence/domain knowledge stressing about how to set up, maintain, and navigate confusing layouts, you've created digital gold.

This isn't the fault of open source services you can only expect so much polish from non-profit voulenteer. Its just the nature of consumer laziness/expectation for professional product standards and the path/product of least resistance.

I really hope the new r1 CoT reasoning patterns get trained into a mistral model, they're the only ones I half count on for decent uncensored base models. Keep an eye on the UGI chart too if thats something you care about. The best uncensored model I ever tried was is beepo 22b IMO.

Surely theres someone else on here who remembers the Delta Heavy - Ghost music video from like a decade ago featuring our boy doing just that? Surprised it wasn't mentioned already.

Thank you! Putting the parts I have now into the pc part picker shows an approximate draw of 334W. Adding 65W on top of that to account for p100 max draw is 400w expected draw. The 1070ti I have has an expected draw of 150W adding that on would draw 550W which seems in range of 700W psu.

Theoretically my current 450w PSU could handle p100 maybe but 50w overhead is slim.

Budget is everything to me right now the 1050W PSU are like 150$ while that 700W psu is 50$. When things aren't so tight and if I get deep enough down the rabbit hole to chain multiple server class GPUs ill probably be in a better spot to afford an expensive psu along with a big batch of cards.