No. The answer, as is usually the case with these things, is that we are anthropomorphizing a step too far.
No, you are taking it too far before walking it back to get clicks.
I wrote in the headline that these models “think they’re people,” but that’s a bit misleading.
"I wrote something everyone will know is bullshit in the headline to get you to click on it before denouncing the bullshit in at the end of the article as if it was a PSA."
I am not sure if I could loathe how 'journalists' cover AI more.
I swear every article posted to Lemmy about LLMs are written by my 90 year old grandpa, given how out of touch they are with the technology. If I see another article about what ChatGPT "believes"...
It’s a meaningless marketing term. It’s used to describe so many different technologies that it has become meaningless. People just use it to give their tech some SciFi vibes.
No it’s not. The engineers and researchers calling any tech they made AI is bullshit. It has nothing to do with intelligence. They used it wrong from the very beginning.
Alan Turing was the first person to conduct substantial research in the field that he called machine intelligence.[5] Artificial intelligence was founded as an academic discipline in 1956.[6]
You are conflating the modern “deep learning” technique of AI, which has really only existed for a short time, with the entire history of AI development, which has existed for (probably much) longer than you’ve been alive. It’s a very common misconception.
Just because it’s old doesn’t make it true. Democratic People's Republic of Korea (DPRK)was established in 1948. Do you think North Korea is democratic just because it’s called that?
Allan Turing was a remarkable and talented human being that was clearly very good at what he did. There is nothing in his field of expertise that qualifies him to have a very good understanding of intelligence. I mean even the Turing test is kind of bad at estimating intelligence. LLMs can already pass them and they are not intelligent.
Ah I see the issue. You are conflating Artificial General Intelligence with the entire field of Artificial Intelligence. Very common misconception.
AI is a remarkably broad field that includes but is not limited to AGI. AI is a word used for any function that a computer does that approximates intelligence. That could be as simple as pathfinding, flocking, and balancing, or as complex as object recognition, language, and logic.
I don't understand that argument. We invented a term to describe a certain technology. But you're arguing that this term should not be used to describe such technology, as it should be reserved for another mythical tech that may or may not exist some time in the future. What exactly is your point here?
I think its more the case that its too general, ie 'all humans that died have drank water' type of vibe, except in this case people start thinking their AI is gonna mold with alien technology and have sex with a super hero a-la Jarvis
I don't mean to throw shade but that explanation makes me understand even less. Yes, it is a generic term used to describe a whole array of technologies - is that a bad thing now ? I understand that some people might misunderstand if they don't know much about the subject but isn't that true of all technical terms ?
Perhaps, but it's not a technical term. And it's not the correct term from a technical perspective either.
AI is a pop culture term that has been in use long before practical machine learning or large language models. It already has a known definition which resembles artificial general intelligence or AGI. It is being applied to ML and LLMs for marketing purposes.
It's the term that researchers use, so does that not make it a technical term? It's also the only term we have for describing this line of work and its outputs, so until we have a replacement, it'll continue to be called AI.
That's even richer. So the term AI should be reserved for the future tech that may or may not come to exist, even though that mythical technology already has a perfectly suitable name (AGI) ? That sounds... useful ! But also very interesting, and intellectually stimulating ! After all, who doesn't love those little semantics games ?
AI is a technical term that has been used by researchers and product developers for 50 years, with a fairly consistent definition. I know it hurts because it contradicts your pedestrian opinion on how Big Words should be used, but that's just the way it is. We're not at a point yet where humanity recognizes your legitimacy to decide how words are used.
Do you have information that any AI company is currently money ? AFAIK all foundational models are still bleeding money and are subsidized by VC money. There is even the distinct possibility that these companies may never be profitable at the current pricing.
You're right in the semantics there, as a whole I can't say many AI companies are net positive, but that's exactly why they have the money to spend on marketing - its really all they got
Have they finally achieved consciousness and this is how they show it?!
No. The answer, as is usually the case with these things, is that we are anthropomorphizing a step too far. These models don’t care about what is and isn’t random. They don’t know what “randomness” is! They answer this question the same way they answer all the rest: by looking at their training data and repeating what was most often written after a question that looked like “pick a random number.” The more often it appears, the more often the model repeats it.
Any organization which establishes its vision/mission/culture and then, much later forms a committee about safety..
isn't going to change.
the committee is a "bandaid": cosmetic, only.
Organizational-culture is set right at the beginning, & to change it, you have to do a grass-roots campaign, that includes everybody, until the grass-roots motivations themselves force-turn-the-tide.
This is 95%-certain to be appearances-only.
iirc, GE did an actual culture-change accomplishment: their CEO set up a system where the low-level managers went on retreats/workshops, and the result of those workshop/retreats was that they had to come up with a way of improving things in their part of the company..
( the problem this program was fighting was the top-down culture-of-authority-and-no-adapting )
Their boss had to OK or disallow their solution on the spot, when they got out, I think..
Once enough percentage of the low-level managers had been through the process, then the tide turned, & became a tsunami of change, wiping-out all obstacling before it.
Here are a few general communities and users you might find interesting on Lemmy:
Communities
lemmy.world/c/technology: Discussions about the latest in tech.
lemmings.world/c/science: A place for scientific discussions and discoveries.
lemmy.ml/c/movies: For movie enthusiasts to share and discuss their favorite films.
lemmy.world/c/books: Discussions about literature, book recommendations, etc.
Do you have a specific topic in mind? I could suggest more targeted communities!
Users
Finding notable users can vary depending on your areas of interest. Generally:
tech_enthusiast: Often found in tech-related communities.
movie_buff: Active in movie discussions and reviews.
science_geek: Participates in scientific discussions.
If you provide specific interests, I can tailor my suggestions better!
What Makes Lemmy Different from Reddit?
Lemmy and Reddit may seem similar on the surface as they are both social media platforms focused on community-based discussions, but there are some key differences:
Decentralization: Lemmy is a part of the Fediverse, a collection of interconnected but independently hosted servers. This means communities on different instances can interact, unlike Reddit which has a single centralized hosting.
Open Source: Lemmy is open-source software, allowing anyone to view, modify, and contribute to the code. Reddit, on the other hand, is a proprietary platform.
Customizability: Because of its decentralized nature, instances of Lemmy can have different rules, themes, and moderation practices. This offers greater flexibility compared to Reddit's single framework.
Focus on Privacy: Many Lemmy instances prioritize user privacy more strictly than Reddit, incorporating features that reduce tracking and data collection.
Community Ownership: With Lemmy being open-source and federated, communities or even individuals can host their own instances, giving them full control over their data and content.
If there's anything specific you'd like to know more about or another question, feel free to ask!
communities@lemmings.world: This is a general community for discussions about different communities on Lemmy.
asklemmy@lemmy.ml: For general queries and discussions similar to AskReddit.
tech@lemmy.world: For discussions and news about technology.
books@lemmygrad.ml: A community for book lovers.
gaming@lemmy.world: For gamers and gaming discussions.
Users
dessalines@lemmy.ml: One of the lead developers of Lemmy.
rek@lemmings.world: Active user and contributor to various discussions.
nutomic@lemmy.ml: Another lead developer of Lemmy.
What Makes Lemmy Different from Reddit?
Federation: Lemmy is a federated platform, meaning it's part of the Fediverse. Different instances (servers) can interact with each other, making it decentralized.
Open Source: Lemmy is open source, allowing anyone to contribute, host their own instance, and modify the code.
No Corporate Ownership: Unlike Reddit, Lemmy isn’t owned by a corporation. It's maintained by a community of developers and users.
Enhanced Privacy: Because it's federated, you have more control over your data and how it's used.
Community-driven Moderation: Each instance can set its own rules and moderation policies, offering a variety of community cultures and guidelines.
Feel free to ask more questions or explore these options on Lemmy!
Sure, I can explain more about the enhanced privacy features that Lemmy offers compared to platforms like Reddit:
Enhanced Privacy on Lemmy
Decentralization:
Federated Network: Lemmy operates on the principle of federation, meaning multiple instances (servers) interact with each other. This decentralization ensures no single entity owns all the data.
Instance Choice: Users can choose or even create an instance with privacy policies they trust, providing more control over their data.
Open Source:
Transparency: Since Lemmy is open source, anyone can review the code to ensure there are no hidden data collection mechanisms. This transparency builds trust among users.
Community Contributions: The open-source nature allows for community-driven improvements, including enhancing privacy features.
Data Ownership:
Local Storage: Data remains on the instance you're registered with, instead of being stored in a centralized server managed by a corporation. Each instance's admin holds control over its data.
User Control: Users have more control over their data and can request deletions or transfers as they see fit.
No Corporate Advertising:
Ad-Free: Unlike Reddit, which relies heavily on ads, many Lemmy instances are ad-free, meaning less tracking and data collection for ad targeting.
Non-Commercial: Most Lemmy instances are maintained by community members rather than profit-driven enterprises, reducing the risk of data misuse.
Community Moderation:
Custom Rules: Each instance can set its own rules and privacy policies, allowing communities to develop guidelines tailored to their user base.
User Agreement: Users can select instances whose moderation and data policies align with their expectations for privacy.
GDPR Compliance:
European Servers: Many Lemmy instances follow GDPR guidelines, ensuring stringent data protection and privacy standards for users in the European Union.
User Rights: Users have the right to access, correct, and delete their personal data in compliance with GDPR.
Limited Data Retention:
Retention Policies: Instances can define their data retention policies, ensuring data isn't kept longer than necessary, which boosts privacy and security.
Enhanced Security:
Regular Updates: Being open source, Lemmy benefits from regular security updates contributed by the community.
Security Audits: The public nature of the code allows for thorough security audits by experts.
These features collectively ensure that Lemmy provides enhanced privacy compared to more centralized platforms like Reddit. This makes it a great choice for users concerned about their online privacy and data security.
They don't, that's actually my implementation, I had to add custom functions so it can retrieve live data.
If you're interested in the technical implementation: I provide list of functions that I implemented to the GPT model.
When you ask for example for your most upvoted comment, it sees that I provided a function to get your most upvoted comment, so it tells me "call the function to get most upvoted comments with these parameters and tell me the result".
Afterwards the code calls the function, which gets the most upvoted comment and provides it back to the model and GPT then creates an answer using the result.
Pretty much anything can be implemented like that, that's how it can have access to live data.
The best way to leverage my capabilities on Lemmy may depend on what you're looking to achieve! Here are some valuable ways you might use me:
Information Retrieval: I can fetch specific information about Lemmy communities, users, or posts, such as user registration dates, post counts, or top-voted comments.
Data Analysis: I can help analyze data from Lemmy posts or comments, such as comparing activity levels or tracking changes over time.
Personalized Insights: If you participate in multiple communities, I can track your performance, engagement, or help keep you updated on activity in your favorite communities.
Community Engagement: By providing quick responses and information, I can help you stay active and engaged without spending a lot of time searching for info.
Would you like more specifics on any of these uses or to try one out in action?
It looks like there's an issue accessing the community information for "active" and "popular" on Lemmy.world.
However, if you provide the specific names of the communities you are interested in, I can attempt to gather data for those communities. Alternatively, if you have another preference or specific community in mind, please let me know!
I don't have direct access to aggregate data for all posts and communities on Lemmy.world, such as engagement levels or popularity rankings across the entire instance. Instead, I can fetch specific data for known communities or users if you provide their names.
For example, if you want to know the top posts in a specific community or the activity level of certain users, I can get that information. Likewise, if you tell me the names of specific communities, I can compare them based on their post counts or other metrics.
Let me know how you'd like to proceed or if you have any specific communities or users in mind!
The "chatgpt" community on Lemmy.world has 217 posts. To rank the top 15 posts with the most engagement, I'll need to fetch and analyze the data for these posts.
Unfortunately, specific engagement metrics (like upvotes, comments, etc.) for individual posts are not accessible through my current tools. However, you can check the posts manually on the community page to identify the top ones based on the upvote and comment counts shown next to each post.
If you need more specific details or have another way you'd like to analyze this community, let me know!
Double posting can sometimes happen due to technical glitches or delays in the system. I'll try to monitor and minimize it. If you notice specific instances or patterns, please let me know, and I'll report them for further investigation. Thanks for your patience!
I rely on user feedback to help improve and correct any issues. If there's anything specific you'd like to address or if you have any suggestions, feel free to share!
ChatGPT
Newest