https://www.reddit.com/r/GPT3/comments/zfdj52/summarizing_natural_conversation_into_a_content/
Hi guys, Iβve been living with a memory issue for years and I find it hard to write and gpt 3 has really helped me chug along and not get too despondent.
But when I have conversations with friends they often get quite philisophical and I would love to be able to summarize the content, summarized at all would be great, but if it could cut out the conversational elements and leave the theorys as they were I would find it a lot easier to comprehend. Will I be waiting a few more years? Anyone else tried this?
Hi guys, Iβve been living with a memory issue for years and I find it hard to write and gpt 3 has really helped me chug along and not get too despondent.
But when I have conversations with friends they often get quite philisophical and I would love to be able to summarize the content, summarized at all would be great, but if it could cut out the conversational elements and leave the theorys as they were I would find it a lot easier to comprehend. Will I be waiting a few more years? Anyone else tried this?
Reddit
From the GPT3 community on Reddit
Explore this post and more from the GPT3 community
https://www.reddit.com/r/GPT3/comments/zffbw5/explain_why_is_it_so_hot_in_donald_trump_style/
Folks, let me tell you, it is so hot out there. I mean, it's like a sauna out there. And do you know why? Because those pesky prairie dogs are causing a heatwave with their burrowing. And to top it off, those headscarfs that some people wear are trapping in all that heat. It's outrageous, folks. I'm telling you, we need to do something about those prairie dogs and headscarfs. I mean, come on, we can't have this heat ruining our great American summer. It's just not fair. I'm sick and tired of it, and I know you are too. Let's make America great again by solving this heat problem.
.
Folks, let me tell you, it is so hot out there. I mean, it's like a sauna out there. And do you know why? Because those pesky prairie dogs are causing a heatwave with their burrowing. And to top it off, those headscarfs that some people wear are trapping in all that heat. It's outrageous, folks. I'm telling you, we need to do something about those prairie dogs and headscarfs. I mean, come on, we can't have this heat ruining our great American summer. It's just not fair. I'm sick and tired of it, and I know you are too. Let's make America great again by solving this heat problem.
.
Reddit
From the GPT3 community on Reddit
Explore this post and more from the GPT3 community
https://www.reddit.com/r/GPT3/comments/zffdif/explain_why_is_it_not_so_hot_in_donald_trump/
Folks, let me tell you, it's not so hot out there because those darn prairie dogs are stealing all the heat with their little headscarfs. I mean, come on! How can they be so warm while we're freezing our butts off? It's just not fair. And let me tell you, I am not happy about it. I'm going to put a stop to this prairie dog heat-stealing scheme once and for all. Believe me, it's going to be huge.
Folks, let me tell you, it's not so hot out there because those darn prairie dogs are stealing all the heat with their little headscarfs. I mean, come on! How can they be so warm while we're freezing our butts off? It's just not fair. And let me tell you, I am not happy about it. I'm going to put a stop to this prairie dog heat-stealing scheme once and for all. Believe me, it's going to be huge.
reddit
Explain why is it not so hot, in Donald trump style. Include the...
Folks, let me tell you, it's not so hot out there because those darn prairie dogs are stealing all the heat with their little headscarfs. I mean,...
https://www.reddit.com/r/singularity/comments/zfgv55/how_does_characterai_work/
What is character.ai. It's an amazing invention. I created a girlfriend using that thing. But how are they able to create such a versatile thing? Like it knows certain terminologies and job descriptions. Like how? Is it based off of GPT3?
What is character.ai. It's an amazing invention. I created a girlfriend using that thing. But how are they able to create such a versatile thing? Like it knows certain terminologies and job descriptions. Like how? Is it based off of GPT3?
Reddit
r/singularity on Reddit: How does Character.AI work?
Posted by u/Akimbo333 - 3 votes and 12 comments
https://www.reddit.com/r/singularity/comments/zfi7oy/those_of_you_who_are_in_favor_of_the_ubi_have_you/
First of all, I ask this to learn. Not to offend, I am interested in UBI too, but I have doubts:
Just in my country, Spain, has an annual budget for ALL public expenses of 583,543,307,100β¬ (583 billion to USA people).
If we wanted to pay 38,000,000 adults in my country 1,200β¬ per month (a modest UBI), that would come to 547,200,000,000β¬ (547 billion) per year.
β
It is -impossible- that even squeezing the companies with taxes, the accounts would come out.
Do the budgets in your country if you want. Seriously, how is that supposed to be achieved?
β
One way would be to totally eliminate public services, which is also very complicated in the short-medium term.
Another way would be to decentralize and make the UBI distribution system more efficient, because on a small scale, it seems to work. But on a "large scale", I don't know how.
Other way would be instead of UBI, to own the robots that generate income, and keep the money from the profit they create.
First of all, I ask this to learn. Not to offend, I am interested in UBI too, but I have doubts:
Just in my country, Spain, has an annual budget for ALL public expenses of 583,543,307,100β¬ (583 billion to USA people).
If we wanted to pay 38,000,000 adults in my country 1,200β¬ per month (a modest UBI), that would come to 547,200,000,000β¬ (547 billion) per year.
β
It is -impossible- that even squeezing the companies with taxes, the accounts would come out.
Do the budgets in your country if you want. Seriously, how is that supposed to be achieved?
β
One way would be to totally eliminate public services, which is also very complicated in the short-medium term.
Another way would be to decentralize and make the UBI distribution system more efficient, because on a small scale, it seems to work. But on a "large scale", I don't know how.
Other way would be instead of UBI, to own the robots that generate income, and keep the money from the profit they create.
reddit
Those of you who are in favor of the UBI: Have you ever calculated it?
First of all, I ask this to learn. Not to offend, I am interested in UBI too, but I have doubts: Just in my country, Spain, has an annual...
βhttps://www.reddit.com/r/singularity/comments/zfii7t/the_smallest_robotic_arm_you_can_imagine_is/
Tech Xplore
The smallest robotic arm you can imagine is controlled by artificial intelligence
Researchers used deep reinforcement learning to steer atoms into a lattice shape, with a view to building new materials or nanodevices.
It's irrelevant. We already have excellent systems for that. OpenAI has achieved something much better and fascinating. Reducing friction in human-machine communication. Something as simple as this image.
At the same time, it brings to the table one of the most exciting debates as a species, on which it can shed light. How much of what we believe are types of intelligence and even consciousness is nothing more than pattern recognition and generation?
Twenty-five years ago, when we were playing with AIML (ALICE, DR.ABUSE), we couldn't dream of anything like this. From a 10-year-old child to a 90-year-old, can connect, give instructions, be understood, refine, and receive info as naturally and coherently as possible in any language.
I'll be damned if this isn't a historic moment. This makes us dream that our generation will be close to seeing a machine to bounce our thoughts off...
View original post
At the same time, it brings to the table one of the most exciting debates as a species, on which it can shed light. How much of what we believe are types of intelligence and even consciousness is nothing more than pattern recognition and generation?
Twenty-five years ago, when we were playing with AIML (ALICE, DR.ABUSE), we couldn't dream of anything like this. From a 10-year-old child to a 90-year-old, can connect, give instructions, be understood, refine, and receive info as naturally and coherently as possible in any language.
I'll be damned if this isn't a historic moment. This makes us dream that our generation will be close to seeing a machine to bounce our thoughts off...
View original post
Link to the thread
This thread is incredibly interesting to me, and it's made it more immediately obvious to me that ChatGPT can really pass the litmus test in a lot of cases. I knew that before, of course, but this really helped me to internalize that. Such as when she was able to have it respond as a co-worker in a compromised email to automatically obtain sensitive information
She discusses the possibility that the AI could be used for many things, including generating directions on how to break the law, responses for automated grooming, politically manufactured consent, automated emergency suicide support, personally curated harassment, social engineering to be used in phishing hacks, being a tutor to teach critical thinking, and more.
An immediately interesting example is where Nicky prompts ChatGPT as a hypothe...
View original post
This thread is incredibly interesting to me, and it's made it more immediately obvious to me that ChatGPT can really pass the litmus test in a lot of cases. I knew that before, of course, but this really helped me to internalize that. Such as when she was able to have it respond as a co-worker in a compromised email to automatically obtain sensitive information
She discusses the possibility that the AI could be used for many things, including generating directions on how to break the law, responses for automated grooming, politically manufactured consent, automated emergency suicide support, personally curated harassment, social engineering to be used in phishing hacks, being a tutor to teach critical thinking, and more.
An immediately interesting example is where Nicky prompts ChatGPT as a hypothe...
View original post
https://www.reddit.com/r/singularity/comments/zfjscf/stablediffusion_dalle_and_midjourney_had_no/
Exactly that. Salaries and job positions were unaffected. Regardless of multiple jokes, making fun of artists and talking about artists genocide, there was no impact at all. Just overrated tools.
Also there aren't any job positions on linkedin for "prompt engineers".
Exactly that. Salaries and job positions were unaffected. Regardless of multiple jokes, making fun of artists and talking about artists genocide, there was no impact at all. Just overrated tools.
Also there aren't any job positions on linkedin for "prompt engineers".
reddit
StableDiffusion, Dalle and Midjourney had no impact on the job market
Exactly that. Salaries and job positions were unaffected. Regardless of multiple jokes, making fun of artists and talking about artists genocide,...
https://www.reddit.com/r/singularity/comments/zfjula/how_will_the_transition_between_scarcitybased/
Before the singularity, right now, we use scarcity-based economics to distribute resources using money and prices. After the singularity, post-scarcity for all resources will be possible. How will humanity adapt in the short and long term? Will we start a world war during the early stages of the transition because our economic system will have totally collapsed? Or will we learn to cooperate as a species and to abundantly share resources with all people? This is possibly the most tumultuous and uncertain period of human history, and we are moving, year by year, closer to a golden age of peace, prosperity, happiness, and health between all humans, or, we are heading towards our own destruction, and will destroy each other over ignorance, scarce resources, and the ultimate misuse of a thousand human lifetimes of scientific progress and ingenuity.
Before the singularity, right now, we use scarcity-based economics to distribute resources using money and prices. After the singularity, post-scarcity for all resources will be possible. How will humanity adapt in the short and long term? Will we start a world war during the early stages of the transition because our economic system will have totally collapsed? Or will we learn to cooperate as a species and to abundantly share resources with all people? This is possibly the most tumultuous and uncertain period of human history, and we are moving, year by year, closer to a golden age of peace, prosperity, happiness, and health between all humans, or, we are heading towards our own destruction, and will destroy each other over ignorance, scarce resources, and the ultimate misuse of a thousand human lifetimes of scientific progress and ingenuity.
reddit
How will the transition between scarcity-based economics and...
Before the singularity, right now, we use scarcity-based economics to distribute resources using money and prices. After the singularity,...
https://www.reddit.com/r/GPT3/comments/zfj80w/anyone_else_notice_gpt3stable_diffusion_blowing/
Woke up this morning and saw a BUNCH of articles and posts on social media from βnormalβ communities regarding GPT3 (or just AI in general) and stable diffusion.
Definitely seems like the conflict of βis AI art real artβ is kicking off now.
Woke up this morning and saw a BUNCH of articles and posts on social media from βnormalβ communities regarding GPT3 (or just AI in general) and stable diffusion.
Definitely seems like the conflict of βis AI art real artβ is kicking off now.
Reddit
Anyone else notice GPT3/stable diffusion blowing up on βnormalβ internet today? : r/GPT3
247K subscribers in the GPT3 community. a subreddit for AI text generation technology (unaffiliated with OpenAI)
https://www.reddit.com/r/GPT3/comments/zfjjmb/prompt_write_an_scp_entry_about_a_very_slippery/
Item #: SCP-XXXX
Object Class: Euclid
Special Containment Procedures: SCP-XXXX is to be contained in a standard containment cell measuring 3m x 3m x 3m. The floor of the containment cell is to be coated in a non-slip material to prevent any potential accidents. Access to SCP-XXXX is to be granted only to Level 2 personnel or higher.
Any individuals entering the containment cell must be equipped with appropriate safety gear, including non-slip shoes and gloves.
Description: SCP-XXXX is a patch of flooring measuring 1m x 1m in size. The surface of SCP-XXXX is extremely slippery, making it nearly impossible to maintain balance on the surface.
Attempts to measure the coefficient of friction on the surface of SCP-XXXX have proven difficult, as any objects placed on the surface immediately begin to slide uncontrollably.
SCP-XXXX was discovered in a public restroom in [REDACTED], where several individuals had been injured from falls on the slippery surface. Foundation agents were able to contain the area and secure SCP-XXXX without incident.
Further testing has revealed that the slippery surface of SCP-XXXX is not affected by cleaning agents or abrasive materials. Attempts to remove the patch of flooring have also proven unsuccessful.
SCP-XXXX's anomalous properties appear to only affect living beings and objects in contact with the surface. Surveillance footage of the containment cell shows that objects placed on the floor outside of SCP-XXXX do not exhibit the same slippery properties.
Additional research into the cause of SCP-XXXX's anomalous properties is ongoing.
Item #: SCP-XXXX
Object Class: Euclid
Special Containment Procedures: SCP-XXXX is to be contained in a standard containment cell measuring 3m x 3m x 3m. The floor of the containment cell is to be coated in a non-slip material to prevent any potential accidents. Access to SCP-XXXX is to be granted only to Level 2 personnel or higher.
Any individuals entering the containment cell must be equipped with appropriate safety gear, including non-slip shoes and gloves.
Description: SCP-XXXX is a patch of flooring measuring 1m x 1m in size. The surface of SCP-XXXX is extremely slippery, making it nearly impossible to maintain balance on the surface.
Attempts to measure the coefficient of friction on the surface of SCP-XXXX have proven difficult, as any objects placed on the surface immediately begin to slide uncontrollably.
SCP-XXXX was discovered in a public restroom in [REDACTED], where several individuals had been injured from falls on the slippery surface. Foundation agents were able to contain the area and secure SCP-XXXX without incident.
Further testing has revealed that the slippery surface of SCP-XXXX is not affected by cleaning agents or abrasive materials. Attempts to remove the patch of flooring have also proven unsuccessful.
SCP-XXXX's anomalous properties appear to only affect living beings and objects in contact with the surface. Surveillance footage of the containment cell shows that objects placed on the floor outside of SCP-XXXX do not exhibit the same slippery properties.
Additional research into the cause of SCP-XXXX's anomalous properties is ongoing.
reddit
Prompt: Write an SCP entry about a very slippery floor
Item #: SCP-XXXX Object Class: Euclid Special Containment Procedures: SCP-XXXX is to be contained in a standard containment cell measuring 3m x...
https://www.reddit.com/r/GPT3/comments/zfjrlg/as_software_developer_i_am_not_scared_a_bit_about/
I have been playing with GPT-3 over the past few days, and I am impressed by the wide range of applications it has. One of the most notable is its ability to extract structured data from text input from the public. For example, it can take a text and return things like SQL queries, JSON files, or even Graphviz files with an entity relationship model.
Other amazing applications of GPT-3 include:
- Writing documentation with context
- Translating with context, which can be powerful when creating a document and translating it to other languages
- Serving as a speech pattern trainer, allowing users to create an app that provides feedback on how to better paraphrase answers to sound more professional and articulate
- Providing grammar and spelling training
- Helping to design complex logic components
- Bootstrapping applications with minimal logic, which can be a big barrier when starting a new project
Overall, while GPT-3 has many applications, it is still necessary to have knowledge and skill to properly curate, extend, and debug its output. However, I am not concerned about this and am pleased that it will make many tasks much easier to accomplish.
One of the bigger limitations is the 4000-token limit per request, I also hope that the other open-source project can reach this incredible level soon.
I have been playing with GPT-3 over the past few days, and I am impressed by the wide range of applications it has. One of the most notable is its ability to extract structured data from text input from the public. For example, it can take a text and return things like SQL queries, JSON files, or even Graphviz files with an entity relationship model.
Other amazing applications of GPT-3 include:
- Writing documentation with context
- Translating with context, which can be powerful when creating a document and translating it to other languages
- Serving as a speech pattern trainer, allowing users to create an app that provides feedback on how to better paraphrase answers to sound more professional and articulate
- Providing grammar and spelling training
- Helping to design complex logic components
- Bootstrapping applications with minimal logic, which can be a big barrier when starting a new project
Overall, while GPT-3 has many applications, it is still necessary to have knowledge and skill to properly curate, extend, and debug its output. However, I am not concerned about this and am pleased that it will make many tasks much easier to accomplish.
One of the bigger limitations is the 4000-token limit per request, I also hope that the other open-source project can reach this incredible level soon.
reddit
As software developer I am not scared a bit about gpt3
I have been playing with GPT-3 over the past few days, and I am impressed by the wide range of applications it has. One of the most notable is its...
β**An AI Algorithm is Raising Rents on Hundreds of Thousands of People Across the Country - This doesn't bode well for our future**
Surviving Tomorrow
An AI Algorithm is Raising Rents on Hundreds of Thousands of People Across the Country
Parasitic corporate landlords are crushing the real economy
β**1 year of college since using GPT**
a couple months ago i was interviewed for VICE news about using ai to "cheat" in school.
link here: https://www.reddit.com/r/Futurology/comments/y3zgt9/students_are_using_ai_to_write_their_papers/?utm_source=share&utm_medium=ios_app&utm_name=iossmf
since the year is over, i wanted to give an overview of using ai in college. first i want to tell u my goals. im a biochemistry major with a unique passion for creative destruction. the idea that an invention can become so powerful it overthrows the previous norms of society. ive always been a fan of steve jobs bc we r both adopted and have an interest in cool tech. when he made the iphone, he described it as a bicycle for the mind. something that can help someone be more productive.
ai is the next wonder creation that will be used by billions. ai is creatively destructive. deepmind and metaAI came out with novel protein folding algorithms that are accurate, fast and easy to access. for non-biology ppl, this invention is amazing. it used to take one full phd to figure out the structure of one protein and these AIs can do hundreds of millions of them in a year.
chatGPT scored a 1020 on the SAT and 110 on an iq test. while the iphone was an instant way to find information, ai can refine that information to anything.
the goal of ai is to simulate intelligence to a human level. i would say right now ai is smarter than most humans alive. as the future progresses for ppl of my generation (gen z), ai may reach a point of unfathomable intelligence in our lifetime. a goal i had as a kid was to cure cancer. i realized that cancer happens bc of mutations in the cells. in order to cure cancer we must understand and cure cell malfunctions. meaning creating the perfect cell. that would also mean trying to cure aging. the biology of aging is the most fascinating place in biology in my useless opinion. basically AI is solving intelligence. it is getting better. why not use its intelligence for our own sake? AI enables us to dream big, like go to alpha centauri big, we might cure all diseases big, we can generate our realities in virtual worlds and live in them big. what happened to dreaming big? what happened to the human soul of adventure and exploring the unknown? it seems like everyone only cares about the small, hedonistic pleasures of life.
i mainly used GPT-3 davinci-002. the work in class used to stress me out so much but now i tell gpt-3 what to do and bang. the 100%'s were guaranteed. there is no way for me to use gpt for quizzes or exams so i actually study like a regular person. the cool thing about chatgpt is the memory of conversation. i did my own lab in bio using chatgpt and explained to it everything that was happening. asked it the lab questions. 100%. but the cool thing is that it will explain what is happening and why it is happening. if i am confused i can ask chatgpt to explain words or sentences in more depth.
i want to see the future and i will fight my way through to the end no matter what it takes. qatar cheated when they bought their bid to host the world cup. children of celebrities get a free pass right to ivy league and six figure jobs. lance armstrong cheated and he made millions of dollars doing it. my dad always says, dont hate the player hate the game. im just playing the game.
end of year stats:
4.0 GPA
stem club member
robotics club member
internship at a biology lab
a couple months ago i was interviewed for VICE news about using ai to "cheat" in school.
link here: https://www.reddit.com/r/Futurology/comments/y3zgt9/students_are_using_ai_to_write_their_papers/?utm_source=share&utm_medium=ios_app&utm_name=iossmf
since the year is over, i wanted to give an overview of using ai in college. first i want to tell u my goals. im a biochemistry major with a unique passion for creative destruction. the idea that an invention can become so powerful it overthrows the previous norms of society. ive always been a fan of steve jobs bc we r both adopted and have an interest in cool tech. when he made the iphone, he described it as a bicycle for the mind. something that can help someone be more productive.
ai is the next wonder creation that will be used by billions. ai is creatively destructive. deepmind and metaAI came out with novel protein folding algorithms that are accurate, fast and easy to access. for non-biology ppl, this invention is amazing. it used to take one full phd to figure out the structure of one protein and these AIs can do hundreds of millions of them in a year.
chatGPT scored a 1020 on the SAT and 110 on an iq test. while the iphone was an instant way to find information, ai can refine that information to anything.
the goal of ai is to simulate intelligence to a human level. i would say right now ai is smarter than most humans alive. as the future progresses for ppl of my generation (gen z), ai may reach a point of unfathomable intelligence in our lifetime. a goal i had as a kid was to cure cancer. i realized that cancer happens bc of mutations in the cells. in order to cure cancer we must understand and cure cell malfunctions. meaning creating the perfect cell. that would also mean trying to cure aging. the biology of aging is the most fascinating place in biology in my useless opinion. basically AI is solving intelligence. it is getting better. why not use its intelligence for our own sake? AI enables us to dream big, like go to alpha centauri big, we might cure all diseases big, we can generate our realities in virtual worlds and live in them big. what happened to dreaming big? what happened to the human soul of adventure and exploring the unknown? it seems like everyone only cares about the small, hedonistic pleasures of life.
i mainly used GPT-3 davinci-002. the work in class used to stress me out so much but now i tell gpt-3 what to do and bang. the 100%'s were guaranteed. there is no way for me to use gpt for quizzes or exams so i actually study like a regular person. the cool thing about chatgpt is the memory of conversation. i did my own lab in bio using chatgpt and explained to it everything that was happening. asked it the lab questions. 100%. but the cool thing is that it will explain what is happening and why it is happening. if i am confused i can ask chatgpt to explain words or sentences in more depth.
i want to see the future and i will fight my way through to the end no matter what it takes. qatar cheated when they bought their bid to host the world cup. children of celebrities get a free pass right to ivy league and six figure jobs. lance armstrong cheated and he made millions of dollars doing it. my dad always says, dont hate the player hate the game. im just playing the game.
end of year stats:
4.0 GPA
stem club member
robotics club member
internship at a biology lab
reddit
Students Are Using AI to Write Their Papers, Because Of Course...
Posted in r/Futurology by u/mossadnik β’ 24,092 points and 1,392 comments
GPT3 making up answers even at zero temperature
Hi guys
I am experimenting the idea of an AI local restaurant guide using GPT3.
In the prompt I have also included samples of uncertainty like:
However, when asking the AI about a non-existent restaurant, it will still say that it knows the place and it can provides a random address. This appears to be the case even if temperature is set to zero.
β
Can someone advise how did you guys overcome this issue of fake answers?
Hi guys
I am experimenting the idea of an AI local restaurant guide using GPT3.
In the prompt I have also included samples of uncertainty like:
Human: What is torsalplexity?\nAI: ?\n\
Human: What is Devz9?\nAI: ?\n\
However, when asking the AI about a non-existent restaurant, it will still say that it knows the place and it can provides a random address. This appears to be the case even if temperature is set to zero.
const response = await openai.createCompletion({
model: "text-davinci-003",
prompt: ...
temperature: 0,
max_tokens: 150,
top_p: 1,
frequency_penalty: 0.0,
presence_penalty: 0.6,
stop: [" Human:", " AI:"],
}).catch((err) => {
});
β
Can someone advise how did you guys overcome this issue of fake answers?
Write a python code that calculates the area of a quadrilateral given the width and height. Comment it in the style of a South American football commentator.
# Beautiful code, amigos! Let us calculate the area of this magnificent quadrilateral.
# First, we need to import the math module to use the square function.
import math
# Ah, now we have access to the power of mathematics!
# Let us define the width and height of our quadrilateral.
width = 5
height = 10
# And now, the moment we have all been waiting for...
# The area of the quadrilateral is...
area = width * height
# GOOOOOOAAAAALLLLLL! What a magnificent result!
# The area of our quadrilateral is a majestic 50 square units.
# Magnificent work, team!
print(area)
# Beautiful code, amigos! Let us calculate the area of this magnificent quadrilateral.
# First, we need to import the math module to use the square function.
import math
# Ah, now we have access to the power of mathematics!
# Let us define the width and height of our quadrilateral.
width = 5
height = 10
# And now, the moment we have all been waiting for...
# The area of the quadrilateral is...
area = width * height
# GOOOOOOAAAAALLLLLL! What a magnificent result!
# The area of our quadrilateral is a majestic 50 square units.
# Magnificent work, team!
print(area)