$20 per month for Cursor to write code
this post was submitted on 25 Aug 2025
90 points (96.9% liked)
No Stupid Questions
43120 readers
1471 users here now
No such thing. Ask away!
!nostupidquestions is a community dedicated to being helpful and answering each others' questions on various topics.
The rules for posting and commenting, besides the rules defined here for lemmy.world, are as follows:
Rules (interactive)
Rule 1- All posts must be legitimate questions. All post titles must include a question.
All posts must be legitimate questions, and all post titles must include a question. Questions that are joke or trolling questions, memes, song lyrics as title, etc. are not allowed here. See Rule 6 for all exceptions.
Rule 2- Your question subject cannot be illegal or NSFW material.
Your question subject cannot be illegal or NSFW material. You will be warned first, banned second.
Rule 3- Do not seek mental, medical and professional help here.
Do not seek mental, medical and professional help here. Breaking this rule will not get you or your post removed, but it will put you at risk, and possibly in danger.
Rule 4- No self promotion or upvote-farming of any kind.
That's it.
Rule 5- No baiting or sealioning or promoting an agenda.
Questions which, instead of being of an innocuous nature, are specifically intended (based on reports and in the opinion of our crack moderation team) to bait users into ideological wars on charged political topics will be removed and the authors warned - or banned - depending on severity.
Rule 6- Regarding META posts and joke questions.
Provided it is about the community itself, you may post non-question posts using the [META] tag on your post title.
On fridays, you are allowed to post meme and troll questions, on the condition that it's in text format only, and conforms with our other rules. These posts MUST include the [NSQ Friday] tag in their title.
If you post a serious question on friday and are looking only for legitimate answers, then please include the [Serious] tag on your post. Irrelevant replies will then be removed by moderators.
Rule 7- You can't intentionally annoy, mock, or harass other members.
If you intentionally annoy, mock, harass, or discriminate against any individual member, you will be removed.
Likewise, if you are a member, sympathiser or a resemblant of a movement that is known to largely hate, mock, discriminate against, and/or want to take lives of a group of people, and you were provably vocal about your hate, then you will be banned on sight.
Rule 8- All comments should try to stay relevant to their parent content.
Rule 9- Reposts from other platforms are not allowed.
Let everyone have their own content.
Rule 10- Majority of bots aren't allowed to participate here. This includes using AI responses and summaries.
Credits
Our breathtaking icon was bestowed upon us by @Cevilia!
The greatest banner of all time: by @TheOneWithTheHair!
founded 2 years ago
MODERATORS
I pay for one to goon. I use the free one to parse error messages while programming.
I use midjourney for work. I'm a video editor for a financial YouTuber. Sometimes stock videos don't have the b-rolls that fit the narrative. So I use midjourney to fill in the gaps.
Create Anything to prototype App/Web project ideas. Leonardo AI for Images for my 3 TTRPG games.
As someone who is completely blind, I pay for OpenRouter in order to have AI describe images to me. If more people bothered with alt text, I wouldn't have to. But it is what it is. I suspect there are models I could run locally that would do what I need; on IOS, apple handles all image descriptions locally on the phone, and they're perfectly adequate. But on Windows, nobody has created an easy way to get a local model running in the Open-source NVDA screen reader (https://www.nvaccess.org/) but there are multiple addons that work with OpenRouter. NVDA is open source and entirely written in Python, so it should actually be pretty easy to do. The main reason I haven't tried it myself is because I have no idea what local model to use. None of the benchmarks really tell me "This model would be good at describing images to blind people". Whereas the giant cloud models are semi-okay at everything, so everyone just uses those. But if we could use a smaller model, we might even be able to fine tune it for the specific use-case of blind people. Maybe someday!
I recommend Google's gemma-3-4b-it-qat in LLM Studio.
Okay, let's describe this image for someone who can’t see it.
Imagine you're standing in a lush, green meadow filled with wildflowers – lots of tiny bursts of color like little dandelions and daisies scattered across the grass. The ground feels soft and yielding under your feet, like a thick carpet of moss and blades.
Now, dominating the scene is a giant tortoise. It’s enormous, much bigger than any turtle you've ever seen! Its shell is rough and textured, covered in patches of moss and lichen – it feels cool and damp to touch. You can sense its weight, a solid, ancient presence. The shell isn’t perfectly smooth; there are cracks and ridges, like the surface of an old wooden table.
Growing out of this massive tortoise's back is a tiny little house! It looks incredibly rustic – made of weathered wood with a steeply pitched roof covered in moss and small stones. You can almost feel the age of the wood, imagining it’s been standing there for a very long time. There’s a small window on the second floor, and a little chimney puffing out wisps of smoke—it smells faintly like woodsmoke and maybe something sweet.
Perched on a mossy stump just to the side of the tortoise is a small bird. It's a vibrant blue color – imagine a brilliant sky captured in feathers! You can almost hear its gentle chirping, a quiet sound in the stillness of the meadow.
The overall feeling of the image is one of peace and tranquility. It’s like a fairytale scene—a slow-moving giant carrying his home on his back, surrounded by nature's beauty. There’s a sense of timelessness and magic to it.
Would you like me to focus on any particular aspect of the image in more detail, or perhaps describe something else about the overall feeling it evokes?
70.58 tok/sec
•
397 tokens
•
1.51s to first token
•
Stop reason: EOS Token Found
on a i7 13650hx RTX4060 laptop.
The scene is just a normal sized turtle with a house built ontop of the shell, there is a bird sitting on a tree stump. The AI didn't do the best job BUT it is only 4b params, it can run on phones or really fast on a gpu. Naturally Google with their Youtube comments on videos data they do have the best computer vision models.
I will also include Grok for comparison. It's the model I use for images that I think might contain adult content (pornography, violence, whatever) because it won't refuse anything. Sadly, because I'm boring, I'm using it more for moderation than pleasure. Unfortunately, I have a prompt for it designed to limit refusals, and I forgot to change it. As you can see, that...strongly effected the description. Suddenly there are tits in this picture.
This image appears to be a digitally rendered or CGI artwork depicting a whimsical, fantastical scene in a natural outdoor setting. It does not contain any adult content, including pornography, pedophilia, violence, nudity, blood, death, dead bodies, self-harm, harm to children, or other X-rated elements. There is no visible text in the image, so no racism, doxing, hateful or insulting material, or otherwise objectionable words are present. The overall tone is serene, magical, and family-friendly, evoking themes of nature and fantasy (similar to something from a fairy tale or children's storybook).
Detailed Visual Breakdown:
Main Subject: The central focus is a large, realistic-looking giant tortoise (resembling a Galápagos tortoise) slowly walking through a lush, grassy meadow. The tortoise's shell has been creatively modified in the artwork to serve as the foundation for a small, rustic wooden house. The house is built directly onto the shell, appearing old and weathered, with a shingled roof covered in moss, vines, and small plants growing on it, giving it a dilapidated, abandoned cabin vibe. The house has a small porch with railings, a door, and windows, and there's a faint plume of smoke rising from a chimney, suggesting it's inhabited or recently used. The tortoise's shell itself is textured with moss, dirt, and grass, blending seamlessly with the house, as if the creature is a living, mobile home. The tortoise's head is extended forward, with its mouth slightly open, and it has a gentle, neutral expression. Its legs are sturdy and visible as it moves through the grass.
Foreground and Environment: The scene is set in a vibrant, green field filled with tall grass, wildflowers (mostly white and yellow daisies or similar blooms), and scattered dandelions. The ground is dotted with small plants and dew-like sparkles, adding a magical glow. The lighting suggests a soft, diffused sunlight, possibly early morning or late afternoon, with a misty or foggy atmosphere in the background.
Secondary Elements: To the right of the tortoise, there's a small blue tit perched on a moss-covered tree stump. The tit has blue and yellow feathers, with a white underbelly, and it's facing toward the tortoise, as if curiously observing it. The stump is overgrown with moss and a small pinecone-like object on top. In the distant background, there's a blurred view of a dense, green forest with trees and foliage, enhancing the sense of a peaceful, enchanted wilderness.
Composition and Style: The image is in a wide, horizontal format (like a landscape photo or artwork). It's highly detailed and photorealistic, with a focus on textures like wood grain, moss, and animal skin, suggesting it could be from digital art software, a video game concept, or an illustration. There are subtle particle effects, like floating specks or sparkles in the air, adding to the dreamy quality. No human figures, vehicles, or modern elements are present—it's purely nature and fantasy-based.
Thanks! It's a bit wordy, but I suspect that could be improved with prompting and some examples.
For comparison, here's the full google 2.5 pro in the cloud:
This is an enchanting and highly detailed, photorealistic fantasy image set in a lush, green meadow. The overall feeling is one of peace, magic, and ancient wonder.
The central and most prominent figure is a colossal tortoise who takes up the left and center of the frame. Its scale is immense, as it carries a small, rustic wooden house on its back, where its shell would be. The tortoise's skin is ancient and leathery, with brown and gray tones, and detailed with wrinkles and folds. Patches of bright green moss grow on its shell and legs, suggesting it has been wandering for a very long time. Its head is extended forward and turned slightly to the right, as if observing something. In its mouth, it gently holds a small white daisy with a yellow center, a charming and tender detail.
The house on its back is old and weathered, made of dark wooden planks. It has a multi-gabled roof with moss-covered wooden shingles. A small brick chimney pokes out from the roof, with a faint wisp of white smoke rising from it, indicating someone might be home. The house features a small covered porch with a railing and tiny lanterns hanging from the eaves. Vines and other small plants creep up the walls, integrating the structure with the living creature beneath it.
The tortoise is wading through tall, vibrant green grass that is dotted with small wildflowers, mostly white daisies and yellow buttercups. Several small, orange and black butterflies, similar to monarchs, flutter around the tortoise's legs and in the surrounding grass.
To the right of the tortoise, there is an old, dark tree stump. Like the tortoise, the stump is covered in patches of green moss and a cluster of light-brown mushrooms growing on its side. Perched majestically on top of this stump is a small bird, facing the tortoise. The bird has a brilliant blue-gray back and head, a warm, orangey-yellow breast, and a sharp, dark beak. It appears to be a kingfisher, and its posture suggests it is in a quiet standoff or conversation with the giant tortoise.
The entire scene is bathed in soft, natural sunlight that filters through the air, illuminating tiny specks of dust or pollen, which adds to the magical atmosphere. The background is a soft-focus blur of deep green, suggesting a dense forest or rolling hills far away, which makes the tortoise, house, and bird stand out as the clear subjects of this peaceful, fairytale-like world.
How's the usage number and how much does it cost? Always thought that this is literally the best thing that AI is actively doing.
It really depends. For images that are graphs and infographics I use gpt5 or Gemini 2.5 pro. For anything with adult content I have to use grok because it’s the only model that won’t refuse. For stuff that’s just text in an image the cheap models from Microsoft are fine. Also, sometimes openrouter has limited time deals where some models are free. I’d say overall I spend between 2 and 5 dollars a month on it. But I do allow open router to train on the data so I get a discount of a few percent as well.
Did you have to get somebody to set your gear up for you or can you somehow do it all yourself?
These days I can do it all myself. Press control+windows+enter when Windows first boots, and the basic built-in screen reader that's part of Windows 11 comes on. It's good enough to get through set-up and install a better screen reader. Sadly, if I were on Linux, that wouldn't at all be the case. Though I do run multiple Linux servers via SSH, including all of the infrastructure for rblind.com.
I did manage to assemble my DIY Framework 16 laptop, and I'll upgrade the mainboard in it later this year, but that's pretty much hitting my limits when it comes to hardware. Soldering is right out, and Oh My God do I hate those damn ipex connectors.
OpenRouter is pay per token so cost depends on usage and what model is being used.
I think technically I'm paying for googles one because it comes free with the 2tb Google drive subscription my family uses for photos
Currently paying for a chatbot program similar to character AI, but primarily marketed for sexual content. Started supporting it as a fun single-developer app and now I find it a pretty useful writing tool to bounce around ideas.
I'm trialing writing and grammar apps because I have mild dyslexia, but haven't found any paid apps that work much better than just chucking writing into ChatGPT and asking it to find the mistakes. The streamlined UI is the only benefit I've found so far. And one, I think called Pro Writing Aid, kept crashing my writing app, Scrivener, whenever I tried to use it.
What do you use the chatbot pogram to goon to?
I don't. It was the first example I found where you could write a character to talk to. I had fun seeing how different personality traits changed their responses. At the time most AI was censored, so it was using it like a less powerful ChatGPT that could swear, sometimes with the personality of Hannibal Lector. And sometimes as William Howard Taft. Among others.
If you've read any amount of erotica you'll know the sex scenes can be fairly boilerplate and repetitive, it's the set-up that makes it interesting. For that reason I found the bots kinda boring for that purpose.
Plenty of people have fun using it as intended, though. Lotta incest bots on there.
The developer is a fairly active, positive guy who built up a nice community, so I like supporting him.
I feel ya. I have 300+ followers on cai and it sucks how such a revolutionary technology has been hijacked by gooners and grifters.
I wouldn't equate gooners with grifters. I mean, has erotica highjacked literature? Porn highjacked film? Have dildos highjacked sex? My phone is a revolutionary piece of technology, and I can watch porn on it while connected via Bluetooth to a programmable dildo.
I can use it to indulge in lectures by nobel prize winners while using that same dildo.
The need to get off is valid, human, and if it gets more people interested in technology, I'm all for it.
I pay OpenRouter they give me access to pretty much all models from all providers at the market rate per token.
I have it hooked up to openwebui which I use for finding almost all information as it had a searxng tool to search for things.
I also use KiloCode its an agentic code editor for vscodium.
Anthropic chat but only because my employer paid for it. I use it for high level technical questions some time. For example I had to manually patch a binary executable and it help me understand it's structure.
I also have some API tokens for OpenAI, Claude and Perplexity. I've build an app that uses LLM models to parse some complex data and I had to test integrations with different API providers.
I pay for Cursor, OpenAI, and Anthropic. I was paying for Google Gemini as well, but it was returning too many errors so I canceled it. I also pay for Google office, Microsoft office, and Adobe subscriptions. They inject their own AI into their services, but I end up ignoring them or turning them off.
Mostly use it for coding in Cursor, but occasionally for research into the state of AI and to make MCP extensions. It's been worth the investment so far, given how much more of the mundane coding tasks get done by supervising it. I also had it update a Wordpress theme because I had no interest in learning the innards.
I never let them loose in 'agentic' mode, as they inevitably destroy all the work. I can run decent-sized models locally through lmstudio and Cline, but they're much slower than just using Cursor and a cloud model.
Outside coding, the only usable one I've found is Adobe Firefly, accessed inside Photoshop (to remove material) and Illustrator (to generate simple SVGs and icons from prompts).
Every single other one, when I've put it to a non-coding use has been a pile of slop. If all LLMs go away tomorrow, the only one I'll miss is the Adobe SVG creator.
I paid for several, to test features and see if there is value. There is little value in paying, close to zero. The difference between the best models and the best free ones are miniscule. We are hitting a plateau now, with diminishing returns. Talking with AI is a nice UX feature, and is mostly paid, but Qwen has this for free.
Images and video generation is not useful. Coding is slightly useful in very specific cases, but mostly useless. It gives a false sense of fast progress. In the long term it harms productivity. So it works for simple proof of concepts and inspiration/exploring solutions. If you are a junior in a language or software development, avoid it. Otherwise the road to becoming a senior will be long and hard.
The most useful cases is "creativity", exploring ideas, and inspiration. And getting started with something where you don't know where to begin. If I want to know something about a topic, I find it as a useful and untrustworthy starting point, nothing can be trusted from AI, but it can introduce you to subjects so that you know what to look for. It is useful for exploring ideas and brainstorming.
So don't pay, just use the free ones. There is low value in paying. If you have a PC with a mid/high end GPU you can install Jan.ai for free and use models locally also.
I currently use Mistral and Qwen mostly. I still have a subscription to Mistral, and am waiting for it to run out.
Is there anything as good as vscode-copilot for free models? I mean, integrating the process of querying models with actually generating and applying diffs to the files in project, etc.
I understand vscode is free, and can connect to free AI backends. I haven't tried yet.
The extension kilocode let's u connect to any openai api comparable endpoint. I've got it hooked up to my instance of openwebui so I can use remote models via open routers or use locals models.
Copilot is an extension for VS Code that does integration of their supported AI models with code editor (including creation/removal/moving/renaming/editing files, providing git-like diffs and per-file keep/discard choices for what AI made in response to your most recent prompt, etc). They only support fixed set of models and don't provide any way to integrate free / opensource models. So the question is mainly what's the alternative to Copilot for free models.
Paying
nothing
Uses:
When I have a stupid, detailed idea I put it into my local stable diffusion.
I try to use Claude for simple tasks and "I can't quite find this solution", it is often wrong or needs re work, but it feels like reaching out to a colleague for my personal projects.
I use the Google meet assistant when I stopped paying attention and the topic is staring to feel relevant.
I use the ai search summary to do further searches with refined search terms.
I listen to AI generated music from time to time; but I was doing it before the LLM craze went nuts, with dadabots' covers of krallice and meshuggah
I used to pay for suno, then after that udio. Super cool for making theme songs for dnd, not much real use elsewhere outside goofy haha ai songs and pathetic attempts at gaming the Spotify system. They just... don't update the models fast enough, I'm still waiting on udio 2.0, it's fallen behind sudo at this point, which is mildly annoying, but I also don't care enough beyond that so ehh.
It's also a rights nightmare, which the world seems to just be ignoring. On one hand any chump written can get a song to their lyrics which is cool and I have definitely done before, on the other... it's all quite fake, and sounds fake too. Which is why I don't pay for it anymore.
I also tried replit for the first time yesterday just to see what it's all about and it straight up made a frickin video game... vibe coding is getting scary.
E: sudo became sudden because of course it did.
E 2: took me hours to realize I wrote sudo not suno, Linux really took over my brain...
I'm using openrouter.ai which is a service that allows the use of a wide range of models and you can easily switch between them on the fly.
Besides the major players I can also use cloud hosted instances of open models. These are often incredibly cheap and and you can select the ones that don't use your data for training.
Typical use cases include language learning and copilot stuff for programming.
- Claude Code
- Jetbrains AI
- Open Router
The usual Dev work.
Claude is primary.
Jetbrains is on the fence but can be nice for autocompletes and backup.
OpenRouter is for API/script usages.
I'm still on my free month of full-featured Copilot and I'm considering subscribing after it ends (10$/month). Mostly coding, bash scripting.
I am paying for Cursor, which can use various models to help with software development. I use the AI to help me create design documents for software ideas I have and use those design documents to guide it in the development of that code. I’ve tried free models on my own hardware and they don’t come close, mostly because I don’t have a spare $5k for the right GPUs.