You must log in or register to comment.
Great for giving incantatons for ffmpeg, imagemagick, and other power tools.
“Use ffmpeg to get a thumbnail of the fifth second of a video.”
Anything where syntax is complicated, lots of half-baked tutorials exist for the AI to read, and you can immediately confirm if it worked or not. It does hallucinate flags, but fixes if you say “There is no --compress flag” etc.
This is the way.
I’m piping my in house camera to Gemini. Funny how it comments our daily lives. I should turn the best of in a book or something.
Another one;
Night Hall Motion Detected, you left the broom out again, it probably slid a little against the wall. I bemoan my existence, is this what life is about? Reporting on broom movements?
Yeah I have a full collection of super sarcastic shit like that.
Do you take any precautions to protect your privacy from Google or are you just like, eh, whatever?
deleted by creator
AI’m on Observation Duty
Absolutely « whatever ». I became quite cynical after working for a while in telco / intelligence / data and AI. The small addition of a few pic is just adding few contextual clues to what they have already.
I’ve done lots of cool things with AI. Image manipulation, sound manipulation, some simple videogames.
I’ve never found anything cool to do with an LLM.
Care to expand on sound manipulation? Are you talking about for removing background noise from recordings or something else?
Some speech recognition work, some selective gain adjustments –not just amplifying certain bands of frequencies, but trying to write a robot that can identify a specific instrument and amplify or mute just that. Also fun with throwing cellular automata at sound files. And with throwing cellular automata at image files to turn them into sound files.
That all sounds pretty neat. Do you do these things locally or is there a cloud service for that?
LLMs are pretty good at reverse dictionary lookup. If I’m struggling to remember a particular word, I can describe the term very loosely and usually get exactly what I’m looking for. Which makes sense, given how they work under the hood.
I’ve also occasionally used them for study assistance, like creating mnemonics. I always hated the old mnemonic I learned in school for the OSI model because it had absolutely nothing to do with computers or communication; it was some arbitrary mnemonic about pizza. Was able to make an entirely new mnemonic actually related to the subject matter which makes it way easier to remember: “Precise Data Navigation Takes Some Planning Ahead”. Pretty handy.
On this topic it’s also good at finding you a acronym full form that can spell out a specific thing you want. Like you want your software to spell your name/some fun world but actually have full form related to what it does , AI can be useful.
Tailored boilerplate code
I can write code, but it’s only a skill I’ve picked up out of necessity and I hate doing it. I am not familiar with deep programming concepts or specific language quirks and many projects live or die by how much time I have to invest in learning a language I’ll never use again.
Even self-hosted LLMs are good enough at spitting out boilerplate code in popular languages that I can skip the deep-dive and hit the ground running- you know, be productive.
I do this as well—I’m currently automating a repetitive workflow for work using python. What’s the latest project you’ve generated boilerplate code for?
It’s good for boring professional correspondence. Responding to bosses emails and filling out self evaluations that waste my time
I’m an author working on an online story series. Just finished S04. My editing was shit and I could not afford to pay someone to do it for me.
So I write the story, rewrite the story, put it through GPT to point out irregularities, grammatical errors, inconsistencies etc, then run it through Zoho’s Zia for more checks and finally polish it off with a final edit of my own. This whole process takes around a year.
Overall, quality improved, I was able to turn around stuff quicker and it made me a lot more confident about the stuff I am putting out there.
I also use Bing image creator for the artwork and have seen my artwork improve dramatically from what Dream (Wombo) used to generate.
Now I am trying to save up to get a good GPU so that I can run Stable Diffusion so that I can turn it into a graphic novel.
Naturally I would like to work with an artist cause I can’t draw but everyone I meet asks for 20 - 30k dollars deposit to do the thing. Collaborations have been discussed and what I’ve learnt is that as times get tough, people are requesting for greater shares in the project than I, the originator, have. At some point when I was discussing with an artist, he was side lining me and becoming the main character. I’m not saying that all artists are like this, but dang, people can be tough to deal with.
I respect that people have to eat, but I can’t afford that and I have had this dream for years so finally I get a chance to pull it off. My dream can’t die without me giving it my best so this is where I am with AI.
You don’t strictly need a huge GPU. These days, there are a lot of places for free generations (like the AI Horde), and a lot of quantization/optimization that gets things running on small VRAM pools if you know where to look. Renting GPUs on vast.ai is pretty cheap.
Also, I’d recommend languagetool as a locally runnable (and AI free/CPU only) grammar checker. It’s pretty good!
As for online services, honestly Gemini Pro via the AI Studio web app is way better and way more generous than ChatGPT, or pretty much anything else. I don’t like using Google, but if I’m not paying them a dime…
Well, if I am going to push this into the project I envision, privacy is going to be key, so everything will be done locally. I have privacy concerns about running on someone else’s hardware regardless of the provided guardrails and layers of protection I can provide for myself.
I used to use Languagetool and Scribens but found my current working model as the best for me at the moment. I will definitely look at options as I move to the next chapter so Languagetool is still an option. Also, I believe they went AI too? At least online?
Well, if I am going to push this into the project I envision, privacy is going to be key, so everything will be done locally.
Reasonable! And yes languagetool has some online AI thing, probably a junky wrapper around an LLM API TBH.
One thing I’d be wary of is… well, showing you’re using AI?
As a random example, I helped clean up a TV show a long time ago, with mixed results. More recently, I brought the idea of making another attempt to the fandom, and got banned for even considering “AI,” with most of them clearly oblivious to how the original restoration was made… I have a little personal writing project going too, and wouldn’t dare bring it up to the fandom either.
I don’t know what’s involved in your project, but be aware that you may get some very hostile interaction if it’s apparent you use diffusion models and LLMs as helpers.
I’ve been planning for two years now on how to successfully put this together.
First thing I realised I would have to learn is tools like Blender, Gimp (which I will likely replace with Krita), etc. cause regardless of how well AI produces, you need to tidy things up.
Then there is story boarding. No amount of AI can replace professionalism. So this is an important skill to have.
Then there are the layouts. All that. I learnt how to use Scribus for layouts and Inkscape is always handy.
My main struggle will be maintaining consistency which has improved consistently over the last two years, and I’ve been reading a ton of comics to learn the sort of views and angles they use.
I can’t allow AI to generate text for me, cause that loses the plot. I might as well just prompt a story up and put it on Amazon and move on. I don’t want to do that. Instead I let it suggest better phrasing, words, basically a better editor.
I also created my own theme and it, very nicely, points out when I lose the plot. I then ask it to point out where my story sucks and it will also point that out. If I run my text through an AI text detector, I get like 1-2% written by AI which I believe any AI language tool would do. It points out where it detects the AI written text and I work on it and remove the text. GPT has a habit of adding its own text and does not stick to the boundaries set.
No amount of AI can replace professionalism.
This!
I don’t want to do that. Instead I let it suggest better phrasing, words, basically a better editor.
This!
Locally, I actually keep a long context llm that can fit all or most of the story, and sometimes use it as an “autocomplete.” For instance, when my brain freezes and I can’t finish a sentence, I see what it suggests. If I am thinking of the next word, I let it generate one token and look at the logprobs for all the words it considered, kind of like a thesaurus sorted by contextual relevance.
This is only doable locally, as prompts are cached so you get instant/free responses ingesting (say) a 80K word block of text.
Apart from avoiding it?
Indeed. I can proudly say that I managed to renew my unfortunately required M365 without the unfortunately included CoPilot trash. And that’s no mean feat, it is a veritable quest through an everchanging maze of clickables to get it this way.
Makes a good litmus test
Finding specific words in an MP3 log file for our radio station. Free app called Vibe transcribes locally.
I’ve used LLMs to reverse engineer some recipes.
Can you make an example?
I can’t be too specific without giving away my location, but I’ve recreated a sauce that was sold by a vegan restaurant I used to go to that sold out to a meat-based chain (and no longer makes the sauce).
The second recipe was the seasoning used by a restaurant from my home state. In this case the AI was rather stupid: its first stab completely sucked and when I told it it said something along the lines of “well employees say it has these [totally different] ingredients.”
Do you just try and describe what it tastes like?
No
This is a very rare use case, but one where i definetly found them very useful. Similar to another answer mentioning reverse-dictionary lookup, i used llms for reverse-song/movie lookup. That is, i describe what i know about the song/movie (whatever else, could be many things) and it gives me a list of names that i can then manually check or just directly recognize.
This is useful for me because i tend to not remember names / artists / actor names, etc.
Employment. I got a job with one of the big companies in the field. Very employee-focused. Good pay. Great benefits. Commute is 8 miles. Smart, pleasant, and capable co-workers.
As far as using the stuff - nope. Don’t use it at all.
Pasting code and error messages in saves time in debugging stupid mistakes.
Before it was hot, I used ESRGAN and some other stuff for restoring old TV. There was a niche community that finetuned models just to, say, restore classic SpongeBob or DBZ or whatever they were into.
These days, I am less into media, but keep Qwen3 32B loaded on my desktop… pretty much all the time? For brainstorming, basic questions, making scripts, an agent to search the internet for me, a ‘dumb’ writing editor, whatever. It’s a part of my “degoogling” effort, and I find myself using it way more often since it’s A: totally free/unlimited, B: private and offline on an open source stack, and C: doesn’t support Big Tech at all. It’s kinda amazing how “logical” a 14GB file can be these days.
…I’ve pondered getting back into video restoration, with all the shiny locally runnable tools we have now.
Do you have any recommendations for a local Free Software tool to fix VHS artifacts (bad tracking etc., not just blurriness) in old videos?
Do you run this on NVIDIA or AMD hardware?
Nvidia.
Back then I had a 980 TI RN I am lucky enough to have snagged a 3090 before they shot up.
I would buy a 7900, or a 395 APU, if they were even reasonably affordable for the VRAM, but AMD is not pricing their stuff well…
But FYI you can fit Qwen 32B on a 16GB card with the right backend/settings.
How do you get it to search the internet?
The front end.
Some UIs (Like Open Web UI) have built in “agents” or extensions that can fetch and parse search results as part of the context, allowing LLMs to “research.” There are in fact some finetunes specializing in this, though these days you are probably best off with regular Qwen3.
This is sometimes called tool use.
I also (sometimes) use a custom python script (modified from another repo) for research, getting the LLM to search a bunch of stuff and work through it.
But fundamentally the LLM isn’t “searching” anything, you are just programmatically feeding it text (and maybe fetching its own requests for search terms).
The backend for all this is a TabbyAPI server, with 2-4 parallel slots for fast processing.
