#ChatGPT best practices
Explore tagged Tumblr posts
escapecart · 1 year ago
Text
The Synergy between ChatGPT and Instagram: Level Up with AI
In today’s digital age, social media platforms have become powerful tools for individuals and businesses to connect with their target audience. Instagram, with its visually driven content, offers a unique opportunity for individuals to monetize their presence and build a profitable online business. With the advancements in artificial intelligence (AI), specifically ChatGPT, and the automation…
Tumblr media
View On WordPress
2 notes · View notes
mybreadsmybutters · 1 month ago
Text
this site makes me feel like a liberal cuck for occasionally using AI to complete assignments like oh my GOD you dweebs dont even fuck with cheating in school!!!
2 notes · View notes
intelliatech · 4 months ago
Text
Top 10 ChatGPT Prompts For Software Developers
Tumblr media
ChatGPT can do a lot more than just code creation and this blog post is going to be all about that. We have curated a list of ChatGPT prompts that will help software developers with their everyday tasks. ChatGPT can respond to questions and can compose codes making it a very helpful tool for software engineers.
While this AI tool can help developers with the entire SDLC (Software Development Lifecycle), it is important to understand how to use the prompts effectively for different needs.
Prompt engineering gives users accurate results. Since ChatGPT accepts prompts, we receive more precise answers. But a lot depends on how these prompts are formulated. 
To Get The Best Out Of ChatGPT, Your Prompts Should Be:
Clear and well-defined. The more detailed your prompts, the better suggestions you will receive from ChatGPT.
Specify the functionality and programming language. Not specifying what you exactly need might not give you the desired results.
Phrase your prompts in a natural language, as if asking someone for help. This will make ChatGPT understand your problem better and give more relevant outputs.
Avoid unnecessary information and ambiguity. Keep it not only to the point but also inclusive of all important details.
Top ChatGPT Prompts For Software Developers
Let’s quickly have a look at some of the best ChatGPT prompts to assist you with various stages of your Software development lifecycle.
1. For Practicing SQL Commands;
Tumblr media
2. For Becoming A Programming Language Interpreter;
Tumblr media
3. For Creating Regular Expressions Since They Help In Managing, Locating, And Matching Text.
Tumblr media
4. For Generating Architectural Diagrams For Your Software Requirements.
Prompt Examples: I want you to act as a Graphviz DOT generator, an expert to create meaningful diagrams. The diagram should have at least n nodes (I specify n in my input by writing [n], 10 being the default value) and to be an accurate and complex representation of the given input. Each node is indexed by a number to reduce the size of the output, should not include any styling, and with layout=neato, overlap=false, node [shape=rectangle] as parameters. The code should be valid, bugless and returned on a single line, without any explanation. Provide a clear and organized diagram, the relationships between the nodes have to make sense for an expert of that input. My first diagram is: “The water cycle [8]”.  
Tumblr media
5. For Solving Git Problems And Getting Guidance On Overcoming Them.
Prompt Examples: “Explain how to resolve this Git merge conflict: [conflict details].” 6. For Code generation- ChatGPT can help generate a code based on descriptions given by you. It can write pieces of codes based on the requirements given in the input. Prompt Examples: -Write a program/function to {explain functionality} in {programming language} -Create a code snippet for checking if a file exists in Python. -Create a function that merges two lists into a dictionary in JavaScript.  
7. For Code Review And Debugging: ChatGPT Can Review Your Code Snippet And Also Share Bugs.
Prompt Examples: -Here’s a C# code snippet. The function is supposed to return the maximum value from the given list, but it’s not returning the expected output. Can you identify the problem? [Enter your code here] -Can you help me debug this error message from my C# program: [error message] -Help me debug this Python script that processes a list of objects and suggests possible fixes. [Enter your code here]
8. For Knowing The Coding Best Practices And Principles: It Is Very Important To Be Updated With Industry’s Best Practices In Coding. This Helps To Maintain The Codebase When The Organization Grows.
Prompt Examples: -What are some common mistakes to avoid when writing code? -What are the best practices for security testing? -Show me best practices for writing {concept or function} in {programming language}.  
9. For Code Optimization: ChatGPT Can Help Optimize The Code And Enhance Its Readability And Performance To Make It Look More Efficient.
Prompt Examples: -Optimize the following {programming language} code which {explain the functioning}: {code snippet} -Suggest improvements to optimize this C# function: [code snippet] -What are some strategies for reducing memory usage and optimizing data structures? 
10. For Creating Boilerplate Code: ChatGPT Can Help In Boilerplate Code Generation.
Prompt Examples: -Create a basic Java Spring Boot application boilerplate code. -Create a basic Python class boilerplate code
11. For Bug Fixes: Using ChatGPT Helps Fixing The Bugs Thus Saving A Large Chunk Of Time In Software Development And Also Increasing Productivity.
Prompt Examples: -How do I fix the following {programming language} code which {explain the functioning}? {code snippet} -Can you generate a bug report? -Find bugs in the following JavaScript code: (enter code)  
12. Code Refactoring- ChatGPt Can Refactor The Code And Reduce Errors To Enhance Code Efficiency, Thus Making It Easier To Modify In The Future.
Prompt Examples –What are some techniques for refactoring code to improve code reuse and promote the use of design patterns? -I have duplicate code in my project. How can I refactor it to eliminate redundancy?  
13. For Choosing Deployment Strategies- ChatGPT Can Suggest Deployment Strategies Best Suited For A Particular Project And To Ensure That It Runs Smoothly.
Prompt Examples -What are the best deployment strategies for this software project? {explain the project} -What are the best practices for version control and release management?  
14. For Creating Unit Tests- ChatGPT Can Write Test Cases For You
Prompt Examples: -How does test-driven development help improve code quality? -What are some best practices for implementing test-driven development in a project? These were some prompt examples for you that we sourced on the basis of different requirements a developer can have. So whether you have to generate a code or understand a concept, ChatGPT can really make a developer’s life by doing a lot of tasks. However, it certainly comes with its own set of challenges and cannot always be completely correct. So it is advisable to cross-check the responses. Hope this helps. Visit us- Intelliatech
0 notes
kariniai · 9 months ago
Text
Strategic Approaches to Generative AI Adoption in Enterprises
Tumblr media
In the past twelve months, the corporate landscape has been abuzz with the potential of generative AI as a groundbreaking innovation. Despite broad recognition of its transformative power, many firms have adopted a tentative stance, cautiously navigating the implementation of this technology.
Is a cautious approach prudent, or does it inadvertently place companies at risk of lagging in a rapidly evolving technological landscape?
Recent investigations forecast the staggering benefits of generative AI, suggesting potential productivity gains in trillions of dollars per annum by 2030 if harnessed effectively.
The rewards surpass the apprehensions, provided the adoption of this technology is executed with strategic foresight. It's not about restricting generative AI but about sculpting its usage within well-defined parameters to mitigate potential challenges, including uncontrolled expenses, security breaches, compliance issues, and employee engagement.
Below, we outline ten strategic approaches for enterprises to capitalize on generative AI effectively and securely.
Adopt a Streamlined Approach to Business Case Development: Generative AI, an emerging technology, demands a departure from traditional business case development. Enterprises should prioritize rapid experimentation and learning to pinpoint practical technology applications swiftly. Discover and Explore
Action Points:
Accelerate pilot projects and proof-of-concept initiatives to cultivate knowledge and skills.
Discover and Explore and Test on repeat
Avoid:
Postponing initiatives due to the need for more absolute clarity.
Over-reliance on cumbersome business case development processes.
Initiate with Straightforward Applications: Before venturing into more complex applications, begin by unlocking value within existing business processes.
Action Points:
Concentrate on internal applications as foundational steps.
Prioritize data readiness for customized solutions.
Avoid:
Early deployment of customer-facing applications due to higher associated risks.
Use case lock where you’re working to solve a specific problem in one particular way.
Streamline Technology Evaluation: Most generative AI tools offer similar capabilities, rendering extensive evaluation unnecessary.
Action Points:
Collaborate with firms like Karini.ai for initial use cases whose platform provides immediate access to no-code tools for operationalizing Gen AI smartly.
Focus on trust and integration capabilities that open your LLMs, Models, and Data to all available options.
Avoid:
Elaborate and potentially outdated analysis of technology providers.
Vendor lock on a single platform that will cause crippling limitations.
Harness External Expertise: The scarcity of AI expertise necessitates partnerships for successful implementation and integration.
Action Points:
Assess internal expertise gaps, seek external support accordingly, and embrace a low-code/no-code platform, i.e., Karini.ai, which will keep the journey quick and safe.
Facilitate technology assimilation into the enterprise.
Avoid:
Isolated attempts at implementation.
Restrictive partnerships limit future technological choices.
Design a Flexible System Architecture: Architectures must be dynamic to accommodate evolving technologies, use cases, and regulatory landscapes.
Action Points:
Foster innovative and forward-thinking architectural design.
Anticipate and plan for future architectural adjustments.
Avoid:
Rigid architectures based on present-day technology functioning.
Over-reliance on existing processes for future technology support.
Implement Robust Security Protocols: Addressing generative AI's unique security challenges through custom policies and robust partnerships.
Action Points:
Develop tailored policies and procedures.
Partner with platforms that are active protectors of your data security.
Avoid:
Dependence on outdated security frameworks.
Technology adoption paralysis due to fear of risk.
Establish Innovative KPIs: New KPIs should reflect generative AI's unique value and impact on business operations.
Action Points:
Develop KPIs centered around long-term value creation.
Learn from both successes and failures.
Avoid:
Ignoring the learning opportunities presented by unsuccessful initiatives.
Foster Open Communication: Ensure continuous feedback and open communication channels for iterative improvement and employee engagement.
Action Points:
Integrate feedback mechanisms into all AI systems, like Karini uses in our CoPilot. 👍👎💬
Maintain transparent communication about AI's impact on the workforce.
Avoid:
Relying solely on conventional feedback methods.
Promote Comprehensive Learning and Development: Equip employees with the necessary skills and understanding to leverage AI tools effectively.
Action Points:
Provide extensive learning opportunities; Gen AI is empowering.
Align learning initiatives with broader change management strategies.
Avoid:
Limiting learning opportunities to direct users of AI tools AI needs to be democratized.
Embrace Iterative Learning: Cultivate a learning and continuous improvement culture to maximize the value derived from generative AI.
Action Points:
Prioritize learning and skill enhancement.
Engage in iterative development to refine use cases and technology applications.
Avoid:
Pursuing overly ambitious initial use cases.
Disregarding the evolving nature of AI technologies.
As enterprises stand at the cusp of this generative AI revolution, adopting a 'wait-and-see' approach may inadvertently place them at a competitive disadvantage.
The promise of generative AI far overshadows the perceived risks, demanding proactive engagement rather than cautious observation. Now is the opportune moment for enterprises to embrace generative AI, navigating its introduction with calculated measures to offset potential risks.
For further insights, explore our website or engage with our team. 
About us:
Fueled by innovation, we're making the dream of robust Generative AI systems a reality. No longer confined to specialists, Karini.ai empowers non-experts to participate actively in building/testing/deploying Generative AI applications. As the world's first GenAIOps platform, we've democratized GenAI, empowering people to bring their ideas to life – all in one evolutionary platform.
Contact us:
Jerome Mendell
(404) 891-0255
1 note · View note
affordableseofl · 10 months ago
Photo
Tumblr media
Understanding And Adapting To SEO Trends In 2024 - #affordableseo #AffordableSEO, #AffordableSEOCompany, #AffordableSEOTampa, #AI - https://www.affordableseofl.com/2024/01/09/understanding-and-adapting-to-seo-trends-in-2024/
0 notes
communistkenobi · 26 days ago
Text
Tumblr media
(taken from a post about AI)
speaking as someone who has had to grade virtually every kind of undergraduate assignment you can think of for the past six years (essays, labs, multiple choice tests, oral presentations, class participation, quizzes, field work assignments, etc), it is wild how out-of-touch-with-reality people’s perceptions of university grading schemes are. they are a mass standardised measurement used to prove the legitimacy of your degree, not how much you’ve learned. Those things aren’t completely unrelated to one another of course, but they are very different targets to meet. It is standard practice for professors to have a very clear idea of what the grade distribution for their classes are before each semester begins, and tenure-track assessments (at least some of the ones I’ve seen) are partially judged on a professors classes’ grade distributions - handing out too many A’s is considered a bad thing because it inflates student GPAs relative to other departments, faculties, and universities, and makes classes “too easy,” ie, reduces the legitimate of the degree they earn. I have been instructed many times by professors to grade easier or harder throughout the term to meet those target averages, because those targets are the expected distribution of grades in a standardised educational setting. It is standard practice for teaching assistants to report their grade averages to one another to make sure grade distributions are consistent. there’s a reason profs sometimes curve grades if the class tanks an assignment or test, and it’s generally not because they’re being nice!
this is why AI and chatgpt so quickly expanded into academia - it’s not because this new generation is the laziest, stupidest, most illiterate batch of teenagers the world has ever seen (what an original observation you’ve made there!), it’s because education has a mass standard data format that is very easily replicable by programs trained on, yanno, large volumes of data. And sure the essays generated by chatgpt are vacuous, uncompelling, and full of factual errors, but again, speaking as someone who has graded thousands of essays written by undergrads, that’s not exactly a new phenomenon lol
I think if you want to be productively angry at ChatGPT/AI usage in academia (I saw a recent post complaining that people were using it to write emails of all things, as if emails are some sacred form of communication), your anger needs to be directed at how easily automated many undergraduate assignments are. Or maybe your professors calculating in advance that the class average will be 72% is the single best way to run a university! Who knows. But part of the emotional stakes in this that I think are hard for people to admit to, much less let go of, is that AI reveals how rote, meaningless, and silly a lot of university education is - you are not a special little genius who is better than everyone else for having a Bachelor’s degree, you have succeeded in moving through standardised post-secondary education. This is part of the reason why disabled people are systematically barred from education, because disability accommodations require a break from this standardised format, and that means disabled people are framed as lazy cheaters who “get more time and help than everyone else.” If an AI can spit out a C+ undergraduate essay, that of course threatens your sense of superiority, and we can’t have that, can we?
3K notes · View notes
technicalfika · 1 year ago
Text
Unveiling the Hidden Potential of ChatGPT: How Scrum Masters can Revolutionize Agile Project Management
In the dynamic world of software development, Scrum Masters play a pivotal role in orchestrating efficient teamwork and ensuring the successful delivery of projects using the Agile Scrum framework. However, the responsibilities of a Scrum Master go beyond just facilitating meetings and removing impediments. To truly excel in their role, Scrum Masters can tap into the untapped power of AI-driven…
Tumblr media
View On WordPress
0 notes
Text
L has been arguing with GlasgowGPT about mythology
Tumblr media
(Important fact GlasgowGPT is leaving out: Oisín was born a deer, due to his mother being a deer. Also seems to be accusing him of incest?)
GlasgowGPT also made fun of me about Transformers but has suspiciously extensive opinions about mediocre 1989 Marvel crossover event Atlantis Attacks
0 notes
creolestudios · 1 year ago
Text
Realize the potential of ChatGPT in customer service! Explore inspiring success stories from businesses that have transformed their customer support using ChatGPT. Gain valuable insights and key takeaways to revolutionize your own customer service journey. Improve response times and deliver exceptional experiences.
Tumblr media
1 note · View note
eymssk-blog · 2 years ago
Text
Can I Write a Book with ChatGPT?
Meta Description: Discover how ChatGPT, an AI language model, can help you write a book. Learn the benefits, limitations, and best practices for using AI in your writing process. Can I Write a Book with ChatGPT: A book can be immensely exciting and enjoyable to write, but it also takes commitment, time, and effort. The thought of using artificial intelligence (AI) like ChatGPT to facilitate the…
Tumblr media
View On WordPress
0 notes
kirantech · 2 years ago
Text
Empowering Content Authors with AI: Using ChatGPT with AEM for Enhanced Assistance
ChatGPT is a large language model trained by OpenAI based on the GPT (Generative Pre-trained Transformer) architecture. I was designed to generate human-like responses to a wide range of natural language inputs. Essentially, I'm an AI chatbot that can con
Tumblr media
View On WordPress
0 notes
marketingtips-allday · 2 years ago
Text
The Role of Artificial Intelligence in Digital Marketing
Artificial Intelligence (AI) has revolutionized many industries, and digital marketing is no exception. The use of AI in digital marketing has transformed the way marketers approach their target audience and has helped them improve their overall marketing strategies. In this article, we will discuss the role of artificial intelligence in revolutionizing digital marketing and how it has made a…
Tumblr media
View On WordPress
0 notes
smartgirrl · 1 month ago
Text
math study techniques
i’m going to break down some of the most effective ways to study math. this subject definitely can feel overwhelming, but with the right strategies, you can build confidence and success.
this is how i got consistent As on my tests!
Tumblr media
mistakes are valuable
go over your mistakes and learn from them – don't move on without fully understanding why something went wrong.
keep an error log – reviewing common errors helps you avoid them in the future.
ngl, sometimes i get disappointed when i don't make mistakes cuz then i don't have a reference point for studying 😭
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
use visual aids
in geometry or algebra, draw diagrams to visualize the problems.
i am a heavy visual learner so if I can, I will draw out every graph and shape.
Tumblr media
here is a simple example of visual notes in math that i took a while ago
use graphing tools to understand functions or inequalities in a tangible way.
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
practice is key
math requires consistent practice – work through as many problems as you can, varying difficulty levels as you go.
don't rush – make sure you truly understand each problem before moving on.
time yourself during practice to build speed and accuracy for exams.
so important for testing! the tests i do best on i spend around 1-2 minutes per question, leaving me with almost an hour usually to review my work.
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
use online resources
platforms like Khan Academy or other math-focused sites can be super helpful for understanding difficult concepts.
personally i use resources like ChatGPT to give me extra problems that i can do before an exam
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
understand, don't memorize
break down formulas – know why and how formulas work to better apply them in different contexts.
if you're in more advanced math, try 'rediscovering' the formula
concepts over shortcuts – shortcuts can help, but deeper understanding will ensure long-term success.
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
ask for help when needed
study groups or tutors can provide new perspectives on tough problems.
don’t hesitate to ask your teacher for help if you’re stuck
trust me, teachers love questions. my teacher practically begs for them so don't be too afraid. spam office hours if you need to.
˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · . ༉‧₊˚. ‘˚ ͙۪۪̥◌ ✧˚ · . ˚ · .༉‧₊˚. ‘˚ ͙۪۪̥◌
thank you for taking the time to read this. if you have any topics that you want me to cover, let me know!!
260 notes · View notes
ellstronaut · 24 days ago
Text
[ ◉¯] tlougram [ ◉¯]
#just a silly AU
Tumblr media
ellie is typing. . . ╰──╮
Tumblr media
ೃ༄
[ ◉¯] ellie’s account reads like a tech-illiterate-social-degenerate
[ ◉¯] girl literally has 3k followers (boggles her mind how it’s even possible) all of varying degrees of sketchiness
[ ◉¯] her bio’s literally just her initials—ew (yep thinks she’s hilarious ) paired with “space is cool ig” [insert shitty space emoji]
[ ◉¯] tbh—she doesn’t really get the whole “influencer” thing (like what is she influencing???)
[ ◉¯] like the only reason she finally caved and made an account to begin with is because dina and jesse practically bullied her into it
[ ◉¯] which shows—her feed is a hot mess of random pics; memes, a random cat video she saved on her gallery
[ ◉¯] and don’t expect to be fed either—her account is D.E.A.D (you’d be setting yourself up for disappointment)
[ ◉¯] definitely the type to forget she even has an account
[ ◉¯] but best believe—when she does post, its spaced out between 2-3 months
[ ◉¯] maybe a handful of artsy-fartsy pics somewhere in between
[ ◉¯] but most of her pics are literally just sketches (she drew at the back of her physics book) random crap she thinks is funny, memes that only make sense to her, n the occasional trip to the museum/nature pics
[ ◉¯] and like a grand total of one—just one selfie (and yes she did delete the rest)
[ ◉¯] fun fact: she may or may not have accidentally liked one of Dina’s/Cat’s old selfies on a burner account
[ ◉¯] tried to do damage control by unliking almost immediately
[ ◉¯] since we’re being messy—(swears she’d kill anyone on site who dares bring that up but whatever) she once got a chat request from a bot thinking it was a real person 💀
[ ◉¯] spent weeks on end flirting and ofc had to gush about it (like the true degenerate she is)
ೃ༄
spacenerd: dude shes hot
제시: whos hot
[spacenerd has sent an attachment]
dinasure: uh ellie
spacenerd: ??
dinasure: gonna hold ur hand when I say this 😃
spacenerd: she replies quick tho plus shes really nice ;)
제시: bet
spacenerd: huh
제시: bro so is siri
spacenerd: siri cant say stuff like rate my tits??
dinasure: issa bot u moron 💀
[spacenerd has sent a voicenote]
▷ 0:00 ───|────── 0:30
dinasure: fuck no
dinasure: bro just block
제시: ^yea pretty sure @bot_bae ain’t real 😭
spacenerd: SHE SO IS
dinasure: chile…anyways so
spacenerd: u know wat
[spacenerd has left the chat]
dinasure: LMAOO cryingsh
dinasure: think u hurt her feelings
제시:no cap that is sad
dinasure: real like how tf u gonna get catfished by a bot and fall in LOVE 🙃
제시: YEAH bro really down bad for ( . )( . )
dinasure: PLSSSJH
[spacenerd has joined the chat]
spacenerd: IT WAS A GOOD BOT OK
dinasure: i have more chemistry with chatgpt
spacenerd: stfu
spacenerd: n D u dont get to come for me when u deadass fucked a twilight bot
dinasure: bitch its called rp
dinasure: n that was like ONE time
spacenerd: me when i lie
dinasure: i like my men less sparkly now!!!
jesse is typing . . . ╰──╮
Tumblr media
ೃ༄
[ ◉¯] unlike ellie—jesse takes his social media presence very seriously
[ ◉¯] got like +8k followers (most of which are girls) cause that man is a snack (duh)
[ ◉¯] his whole vibe is mellow but cool
[ ◉¯] like his IG feed reads like an episode of Crazy Rich Asians (with the extra added thirst traps of course)
[ ◉¯] aka a perfectly curated mix of aesthetic photos, artsy shots, friends/family and ofc his dog Yeontan
[ ◉¯] definitely the type of boyfriend to post unflattering pics of his gf but not out of malice
[ ◉¯] but you know in a—i’m obnoxiously in love sorta way
[ ◉¯] he may be bilingual but he’s very much in touch with his culture—like dude got a bunch of pics of him back in the Motherland
[ ◉¯] ellie low-key tries to get him to teach her a few curse words in Korean but like 99% of the time ends up teaching her the wrong words instead
[ ◉¯] ofc his username is in hangul— (if anything it’s to make his mom happy—because yes he follows her back on Insta)
[ ◉¯ ] and yes he’s such a boy mom—dina and ellie give him a ton of shit for it
ೃ༄
spacenerd: totally know what that means frfr
dinasure: oppa?
제시: 죽을래?
google translation: you want to die?
[ ◉¯] it’s an inside joke, lord knows how many kpop stans flood his dms—in which he makes the point to block them on site (as he should lol) because korean he may BE—your oppa he is NOT
[ ◉¯] yeah—he makes it pretty damn clear in his bio “yall gotta stop with the BTS shit”
dina is typing . . . ╰──╮
Tumblr media
ೃ༄
[ ◉¯] Dina’s THAT bitch
[ ◉¯] got like +30k followers—is the whole package; hot—effortlessly cool, funny, charismatic (it’s literally unfair)
[ ◉¯] ofc she’s been scouted by at least three modelling agencies
[ ◉¯] and her pictures? flawless—we’re talking gorgeous—goddess-esque—baddie
[ ◉¯] literally the worst part about being friends with Dina: is how ridiculously photogenic she is
[ ◉¯] can roll up out of bed, unshowered, bare-faced and still look hot af (god has favourites I suppose)
[ ◉¯] definitely the type to have the most engagement (via replies, comments, shares, tagged—you name it)
[ ◉¯] absolutely loves sharing her hot girl adventures/outings—fr the embodiment of hot girl summer
[ ◉¯] expect an assortment of her hiking, visiting galleries, cafés, festivals + parties, and of course her many different fits (not that anyone’s complaining)
[ ◉¯] bio reads: my mom thinks I’m cool
[ ◉¯] don’t get me started on her simps—if delulu were a person, it would be Dina’s cult of fanboys
[ ◉¯] one time a dude wrote her poetry—straight up typed a whole ass sonnet ( Shakespeare reincarnate but in simptongue)
[ ◉¯] in which of course her friends had to add their two cents
ೃ༄
spacenerd: its always ily but never
spacenerd: my queen i kneel, my heart it weeps 😞
제시: lmaooooo 💀
[ ◉¯]not just down bad— we’re talking the most absurd, thirsty/depraved comments—
whitedevil commented: Id let you ruin my life
christian.not.jay commented: feet? 🤤
chrislovesyou commented: looked at my girl and sighed
ೃ༄
[ ◉¯] imagine the heartbreak if they ever found out she has a whole ass man (cue what does she SEE in him)
[ ◉¯] so much salt it could fill a whole an entire ocean
cat is typing . . . ╰──╮
Tumblr media
ೃ༄
[ ◉¯] Cat’s account oozes creativity—doodles, sketches, watercolour—digital art the whole nine yards
[ ◉¯] her feed is basically one giant art gallery—like an extension of her art portfolio
[ ◉¯] so if you’re looking for an artsy feed, look no further
[ ◉¯] def an alt girlie (lowkey goth/punk lite) aka dark and edgy but with a soft side to her
[ ◉¯] and by lowkey I mean a beautiful—soft, kind of morbid artistry
[ ◉¯] the vibes she exudes with the outfits, piercings, the makeup and tattoos? (Chefs kiss) high key hot but intimidating
[ ◉¯] not too keen with the whole parasocial thing— “eh it’s nice having people look at my work, but not for me” kinda vibe
[ ◉¯] the type to solely use it for promotional purposes that and activism (btw NOT just for the brownie points like would deadass go outside, touch grass and do something about it)
[ ◉¯] definitely advocates for the environment—supports charities and organizations who fight against systematic oppression (racism, misogyny, etc.)
[ ◉¯] which is one of many reasons why Ellie’s got a huge fat ass crush on her (if it wasn’t already so obvious)
[ ◉¯] proudly Asian—wears it like a badge of honour and is the first to call out racists (and homophobes) any KIND of bigotry tbh
[ ◉¯] her bio reads—“life’s too short for shitty music” and “gay btw” :)” y’know for the losers that might need a little disclaimer
[ ◉¯] not a fan of stupid Asian stereotypes
[ ◉¯] you just know she gets a ton of gross fetishizing DMs (like why do they ALWAYS have an anime pfp)
[ ◉¯] because ruthless she can be with her clap backs
ೃ༄
tagging my besties @bonnibelblanca @adhdprincess ily
132 notes · View notes
physalian · 2 months ago
Text
Fuck Grammarly
Tumblr media
Okay I need to rant about Grammarly. A program I never used before and never will now. Doubly pissed because their ads keep interrupting my peaceful 4-hour Minecraft music session with their fake-ass influencers.
Guys. Gals. Nonbinary pals.
“As a corporate girlie—” learn how to write a proper concise email.
“I used to spend hours proofreading—” enjoy the process, and then the product.
If you hate proofreading, to the point where you’ll consult a robot to do it all for you, then you hate writing. If all you care about is the end product, sorry to say but ‘writing’ is like, 30% of writing. The other 70% is editing, by design. You’re supposed to like it.
Of course I’d love to have beautiful artwork of whatever’s in my head, but I’m going to love whatever I make a whole lot more than whatever I type into some garbage generator. Because I love the process of creation.
Do I think editing is tedious as hell? Absolutely, but it’s still a tedium that I enjoy. I like fixing my mistakes, I like improving my sentence flow. I like thinking about patterns and connections that I didn’t see before and revising and reworking until I’m satisfied.
For the humdrum day to day work emails that some of us have to write—if you’re sending out whole essays to your coworkers that you need a robot to write for you, you’re doing it wrong. Corporate emails are boring and trite, but I can type out a “hey please do this thing for me” faster than I can load up ChatGPT or Grammarly, type out my prompt, make sure the result is what I actually want to say, and then send it to my coworker. If you can’t, learn.
Apparently, Grammarly used to be a helpful way to check for spelling and grammar errors. I don’t have any issue with the AI that runs spellchecker whatsoever. I type so fast and miss typos constantly and when the spellchecker is absent, like on this website, it’s annoying af.
But that’s not what Grammarly is about anymore, and that’s not what the above ad was trying to sell you, either.
You won’t get better if you don’t practice. You won’t get better if you aren’t the one making, seeing, and fixing your mistakes. Especially if you write fiction where grammar rules are a suggestion at best. My published novel is littered with flagged words and sentence fragments that I know are technically improper English, but I sacrificed an MLA-proof paper for something fun and entertaining.
AI does not understand nuance and flavor text and aesthetic choices. It never will.
If you train yourself by using a crutch you don’t need, you will end up needing it because you’ll be too afraid to act without it.
Fuck up. Make a mess. Make mistakes. You won’t make them for long once you see them. You do not need a robot to do it for you. We’ve been writing books for hundreds of years and all the authors who came before did it just fine without a robot.
This isn’t even about writing novels, it’s about communicating in the written medium. Fucking. Learn. It’s not rocket science, it’s not coding in C++, it’s not brain surgery. It’s stringing words together in a comprehensible sentence.
And obligatory disclaimer: To anyone who has an impairment and needs these tools, this is not about you and you know it.
84 notes · View notes
chaos-in-deepspace · 1 month ago
Text
Tumblr media
Can't believe I gotta do this, but okay...strap on in guys because this isn't only a rant, but informational. Gonna show you how to clock AI writing, why it's bad, how to abuse AI for writing, and how to prove something was written using a chat bot.
Tumblr media Tumblr media Tumblr media
Have you ever read a fic and had to pause for a moment? Contemplate a few things? You almost feel like a few times you just couldn't figure out. Or perhaps you saw something that just read super awkwardly.
If this describe you reading some fics, then you might've fallen victim to "AI Writers". Yes, that's correct! A writer who uses AI to help them write their fics. Mind you most people when using this method actually use chatbots! So it's not like they just run into ChatGPT, give it a prompt, and then post it. Oh no. They RP it, maybe clean it up a little so it reads more like a fic, and then they post it.
If any of you are use to RPing with Chatbots like Janitor.ai, or even C.ai, then you might occasionally read a fic and realize it's strikingly familiar to chat you read in your own chats. I, for one, dabble in RPing with bots when I get bored, which is how now and days I can read a fic, see certain lines, and just know.
Tumblr media Tumblr media Tumblr media
Now I'm certain I don't need to sit here and explain why this is so bad. However, I'll explain anyways if you'd like to hear my opinion, as well as many other artists and writers:
AI is Plagiarism!
Ya, this is plagiarism. How do you think it's generating responses? Or for artwork, where do you think it's grabbing the images from. It doesn't do it itself. AI is basically giving a program information so it can generate things. A lot of programs that uses AI, as well as websites, uses that written information to generate your responses. You know Google Docs? Ya, it can take information from your writing there. Archive of Our Own? Bingo. Tumblr? Ya, it takes writing from here as well. That means the people who have spent a lot of time on their writing, spending years honing their craft, are having their writing styles and voices stolen from AI in order to make those generated responses. Now when it's just you RPing something, pop off. It's just you and your bot. Share it with a few friends, sure! If you post it online though, those words are a mashup of millions of stories written and posted online. So it's plagiarism. Plain and simple.
2. It sets you back as a writer
Ever wondered why some people can write the most amazing things ever? It's because they wrote. They learned. They practiced. It took time and effort in order to build up those skills. They got there by writing. So how is using AI affecting your writing? Easy, you're not writing. At least...not a lot. If you use a chatbot to write half the things in a fic, you're only doing half the work. You're also bouncing off the idea from your bot and going with it, instead of using your writer brain to figure out how this scene would best be executed. Imagine it like this. Someone uses AI to draw an image for themselves. Then they trace over it, add a few of their own touches, and color it the best they can. Did they suddenly learn how to draw? No. Because they didn't take the time to learn why something is placed like this, how the composition works, etc. Same thing with writing. If you're using AI to do all the work then you aren't learning, and you're not going to be getting better as a writer. If that's the case...why are you writing? It should be a fun experience to write, after all. It should be something you want to get better at. So why are you just having AI do it? Attention? You realize your fics need to be pretty well written to garner attention, right? That brings me to my third point.
3. We can tell...and it's not fun to read
Today a friend showed me an paragraph from a fic he found here on tumblr. I saw it. Without even having to ask I knew it was written by AI. Nobody talks like that except a robot. The wording? Repetitive for AI to use. "Their bond grew with every passing moment." | "Their shared connection." | "His voice was barely above a whisper." | "It was a testament to their relationship." | "He's determined to face this challenge with her, hand in hand, and to make the most out of the second chance he's been given." | "A renewed sense of purpose." | "He's determined to face this challenge with her" If I see these lines, I clock it as Janitor in a heartbeat. Sure, not every time it's used is AI, but those are the most common things I see in every RP with a bot, and I actively need to correct the bots or else they'll use it in every fucking reply. Another thing is...RPs read differently from a fic. They're not made to be read like a narrative story. It's a bot replying to someone, so when you do that things get weird. Not to mention sometimes clothes appear and disappear, a position is changed, etc. It's just not good writing...
4. It's lazy
Simple as that. It's fucking lazy to get AI to write a fic. Trust me, I am one lazy motherfucker. I hate doing things. I want to sleep for literally a solid week. However I made the decision to write things, so I write them. I put in the effort. Other writers who don't use AI? They put in the effort. I know at least 20 people who are depressed as all hell, can barely get out of bed unless it's to go to work, who decided to still write. Not everyone is going to be a fast writer. Not everyone is going to find writing easy. If you're going to commit, though, commit to it. Write it. Don't use AI.
With these points being made, I'm sure you can see why in the writer community, it's frowned upon to use AI as well as bots for your writing...especially when you don't disclose it. I could probably put everything aside if you just said it was written using AI. Honesty is the best policy.
People might not want to read it then, but at least they know that you used AI. At least you admitted to it. Using AI and then passing it off as completely original is disgusting.
Tumblr media Tumblr media Tumblr media
So you clocked something as AI written. You’re pretty freaking sure this was written with a Chatbot. So you plug it into an AI checker and what? No AI detected? No fucking way.
Yes fucking way.
The detectors use a range of things like: Language Model Comparison, Repetitive phrases and structures, contextual awareness, among a few other things. Now look at the "Language Model" part. What if a Chatbot doesn't have the most common language models? It doesn't detect it as easily, that's what.
Where does that leave Chatbots? Well, it means it’s not really checking for things like Janitor or C.ai. A lot of times it flies under the radar because of this. I have found that there is at least one site that doesn’t do this. Instead of more or less checks the context of the text to see if it was written using AI, rather than relying on ai models.
Quillbot
This is what I use to check. I also did run it through some tests. Mind you, not every program is going to be completely accurate. This just happens to, after thorough testing, be the best at being able to tell if a chatbot was used.
Tumblr media
As you can see here, the one on the far left is a fic that I ran through that was my own writing. In the middle I had copy/pasted my own responses, and my bot responses from Janitor. On the far right I pasted only Janitor responses. While it’s not accurate, it could still detect human written from a chat bot!
Tumblr media
In comparison to me running it through other AI Detection softwares (one of them being Grammarly), where they detected nothing in the post that were written by both me, and the bot.
The entire reason I’m even making this post is because I happened to come across a fic that seemed like it was written using AI, so I was curious and ran it through. Mind you, the detection software only lets you paste 1,200 words of the writing, so this was just a snippet. The same size snippets that I had put for all of my own tests. This was the result:
Tumblr media
So we can make a good guess that this was…probably written by AI. If you’re wondering, no. This isn’t a call out post. I won’t be stating the user who I did this. I ask you not to speculate in the notes of this post either. I don’t want to cause unnecessary drama, because honestly the writing community for this fandom already has that.
I will say, to the writers who are using AI, I’m not the only person who will probably get curious. If you’re going to use AI for your writing, at least state it in the description. It’s manipulative and wrong to not state it.
Tumblr media Tumblr media Tumblr media
I know I said AI is bad, but it's also like Thanos. It's inevitable. I fully think we should abuse the hell out of it and make it our bitch. Now how to do that without using it to actually write? Easy.
Force it to give us ideas. Once upon a time I wanted to do some writing, but couldn't think of anything I wanted to write. Sure there's prompt lists out there, but a lot of them didn't fit what I needed. So I grabbed ChatGPT by it's lil grimy throat. I whispered in it's ears "Write me some prompts."
I then took said prompts to jog some ideas in my head, then wrote my own original content. I used AI to help give me a basic idea for my writing and then came up with my own stories. That's a simple way of doing it.
I know people who will RP with a janitor bot because they have a plot in mind for a story, but are uncertain with how they'd want to execute it. So they RP with a bot first, and then once they have an idea, they write a fic based off their RP. They don’t take what the bot said, copy/paste it, then say it’s their fic. They use it as a tool to help them with their ideas. Sometimes if the bot has a really good line, they might take that singular line from it as well. That’s not taking the entire story, it’s just a line that they knew would flow with the fic, and half the time they edit the line as well.
You can also use it for story titles. Can’t come up with a title? Tell ChatGPT the synopsis of your story and then ask it to generate 10 titles for it (actually I just tried to this see the results and am currently laughing my ass off, maybe don't do this).
Don’t forget things like Grammarly. That’s also AI! You can use it to check your grammar and fix awkward wording in your writing.
There’s ways a writer can use AI as a tool. In my opinion, it’s no different from an artist using the symmetry tool for their art. Or using a 3D model to help them make a pose for a drawing in their program. It’s a tool that should be used to help and improve your own content.
56 notes · View notes