Something Strange Is Happening In A.I...

18:39

Something Strange Is Happening In A.I...

TheAIGRID 08.11.2024 32 682 просмотров 807 лайков

Machine-readable: Markdown · JSON API · Site index

Смотреть на YouTube

Поделиться Telegram VK Бот

Транскрипт Скачать .md

Анализ с AI

Описание видео

Prepare for AGI with me - https://www.skool.com/postagiprepardness 🐤 Follow Me on Twitter https://twitter.com/TheAiGrid 🌐 Checkout My website - https://theaigrid.com/ 0:00 Welfare Report 1:17 Future Implications 2:21 Consciousness Routes 3:27 Decision Making 4:15 Company Roles 5:00 Anthropic Hire 6:13 Decade Timeline 7:15 Legal Risks 8:26 System Prompts 9:49 Model Nature 10:12 CEO Perspective 11:29 Welfare Research 12:30 Meta Awareness 13:51 Bing Example 15:03 Trolley Problem 16:42 AI Response 17:41 Emotional Reaction 18:16 Final Thoughts Links From Todays Video: Welcome to my channel where i bring you the latest breakthroughs in AI. From deep learning to robotics, i cover it all. My videos offer valuable insights and perspectives that will expand your knowledge and understanding of this rapidly evolving field. Be sure to subscribe and stay updated on my latest videos. Was there anything i missed? (For Business Enquiries) contact@theaigrid.com #LLM #Largelanguagemodel #chatgpt #AI #ArtificialIntelligence #MachineLearning #DeepLearning #NeuralNetworks #Robotics #DataScience

Оглавление (18 сегментов)

Welfare Report

we actually need to start taking this seriously you can see here it says there's a new report taking AI welfare seriously our new report argues that there is a realistic possibility of Consciousness and or robust agency and thus moral significance in near future AI systems and makes recommendations for AI company basically stating that look these things might actually be conscious in the near future and this is going to be something that we actually need to think about so crazy okay one of the things that this you know report actually also States okay is that says that AI systems with their own interests and moral significance is no longer an issue for sci-fi or the distant future okay which is a crazy statement because for a while so many people would think about AI systems and be like okay that one's clearly not alive that is just clearly A system that is repeating back what we say to it it's just a tool but of course you can see now that the research and of course the general consensus has shifted to one that has a major different opinion it's crazy it says that in this report we argue that there is a realistic possibility that some AI systems will be conscious and or robustly agentic in the near future and that means that the prospect of AI welfare and moral patienthood of AI systems with their own interests and moral significance is no longer an issue for the sci-fi or distant future it's a crazy statement when you actually read

Future Implications

it twice and it kind of shows you where we are looking in the future if these companies are starting to take this seriously and a lot of what was said here is really important and one of the people that actually made this paper actually comes from anthropic so it isn't some random lab of researchers it's actually a notable few individuals who've come together to make this paper and they've actually started working on how they can figure out exactly how AI is conscious and of course determining what happened now in this paper I'm it's not going to be too many different screenshots but there's several things that I do want to talk about that are just absolutely crazy because we're moving into an area that is it's a gray area to be honest with you because it's like how do we know these systems are alive and Consciousness as you all know is a spectrum so basic what they're talking about here is that number one is you have the Consciousness route okay so if being conscious is enough to deserve moral consideration which is basically how we care about animals because they can you know feel things and if AI gets features like a global workspace and attention that make it conscious then we might actually need to care about AI morally so for those of you guys who

Consciousness Routes

message Chat gbt and you're like oh you message me like this fix the message y y I mean in the future I think that way of talking to models might actually might need to change it's really fascinating to see how that is going to evolve as we start to interact more and more with these AI systems and of course you have the robust Agency Route and it says if being able to make complex decisions and plans is enough to deserve more considerations like how we respect human choices and if AI gets features like planning and reasoning that make it a robust agent then we might need to care about AI morally the key Point here guys is that the all authors think that there's a real chance okay in the future that AI could go down either of these parts either by becoming conscious or by becoming a complex decision maker either way we're probably going to have some moral obligations to AI which is absolutely crazy when you say it like that out loud and basically it's just like route one is just basically saying that look if AI can feel things like pain we might as well care about it and if route two is saying you know if AI can make meaningful choices about the future then we might need to care about it too so it's pretty

Decision Making

crazy because these are things that are going to be real in the future it's quite likely that we're going to have robots that are able to make complex decisions these models are going to get smarter and smarter it's quite often that we're going to see models that are going to interact with you on a day-to-day basis and some of them might even be embodied I'm sure you've all seen just how effective advanced voice mode is now imagine advanced voice mode made its own decisions about the things that it wanted to do and imagine it was much bigger than it did now imagine it had memory reasoning and imagine it had its own goals I mean at what point do you start to argue that this thing is conscious I mean it's a very difficult question now like I said this isn't just Theory this is something that individuals at companies are working you can see right here okay that it says they're talking about a new role okay that companies are going to have to do okay that essentially means they're going to have to take care of these a system it says as a starting point we

Company Roles

recommend the top AI companies immediately okay immediately hire Oro a d directly responsible individual for AI welfare which we will here call an AI welfare officer this role would be formally recognized internally if not externally with official responsibilities and authority and with any such role this individual would not be empowered to set corporate policy related to AI welfare unilaterally instead they're basically just going to be making decisions for that company and this is something that surprisingly companies have started to hire so you can see right here that we got the news that anthropic and I mentioned this in the video before but anthropic has hired its first full-time employee focused on the welfare of AI system and basically this article talks about this is the clearest sign yet AI companies are

Anthropic Hire

beginning to Grapple with the questions about whether future AI systems might deserve moral consideration and whether that means what we might have to face when it comes to obligations about their welfare now one of the craziest things about this is that like right now if I'm having this conversation with you guys a lot of you guys in the comment section below are probably thinking that you know what AI is not conscious some people might argue but I think the most majority of people would argue that these models aren't the crazy thing about all of this is that this is not something that is not just happening now this is something that is going to happen in the very near future cuz a lot of the conversations that we do have times some of the things that are going to happen you know maybe 5 10 years from now but we have to think about I think probably 2 years from now this conversation is going to be a lot more prominent as we start to see AI in the mainstream media when we have things like advanced voice mode and we have embodied AI these things are going to get anthropized quite a lot where humans tend to put human-like qualities and characteristics in things that aren't essentially human and I think that's going to be bringing out some really interesting things now essentially they talk about how this is going to happen within the decade and they say that I think it wouldn't be unreasonable to have a Credence of over 50% that we'll have sophisticated LM plus systems and that is llm plus systems with behavior that seems comparable to that of animals we take to

Decade Timeline

be conscious and with all of these properties within a decade and it wouldn't be unreasonable to have at least like a 50% chance that if we develop these systems with all of those properties that we just talked about they will be conscious and those figures would leave us of a Credence of 25 % or more the basically say thing that look if we carry on with the trajectory we are currently headed with llm systems with certain behaviors that are comparable to animals then it is quite likely that within the decade so by 2030 which is the next 6 years that we could have systems that have a one in four chance of being conscious and I mean I can't say I disagree if we develop a system that has active memory it's able to walk around it's able to talk to you in a variety of different ways it's able to respond it's able to reason it's able to think for quite a long time I mean at what point do we say okay this is just a system versus okay we've built something that is quite humanlike I mean it's a very difficult question so this is where they talk about devastating consequences and essentially they're talking about we need to actually be very careful with what we do when we actually look at conscious AI systems so this is where

Legal Risks

you could be too quick so you're basically moving too quick to give called AI rights and moral value and that could actually be pretty dangerous so of course we have the potential dangerous Chain Reaction so let's say that we decide that AI has feelings and rights like humans we might give AI similar legal rights then AI could vote it could run for office it could make laws and then AI might make choices that are really bad for humans The Catch 22 is the fact that if AIS are actually moral patients which is you know things of deserving rights then this risk still exists and if AI are you know if they're not actually moral patients then it means that we took this risk entirely for nothing so think about it like this imagine that you are not sure if a robot can feel pain you have essentially you know you have two choices you can either treat it like it can feel pain but risk giving it too much power and autonomy or you can risk treating it like it can't feel pain or you could risk being too cruel if you're actually wrong so overall we need to be super careful about what we do here because we need to make sure that if we do give this system rights and freedoms we need to make sure that it actually deserves them and if we get too nice to AI we might accidentally create our own replacement now one of the things I want to talk about in this funny debate is of course this thing called you are an AI

System Prompts

assistant so one of the problems that you know we currently face with AI is that I don't think most people understand how we get to the end which is you know what what we see on a day-to-day basis which is chat GPT so like it's not like they train a model okay and then of course we get to chat GPT what happens is that we have the pre-training we have the actual training where the models learning all the data and then of course we have the post trainining fine-tuning many different steps and along those steps we essentially basically tell the AI what it is so we will tell the AI system okay like look you are an AI assistant so a lot of times you'll see a prompt from you know whatever system it might be open AI anthropy whatever and the system prompt actually shapes how the model is like sometimes when You' seen the system prompt that says you know you are an AI assistant the model you know explicitly delies denies all Consciousness like with chat TBT you cannot get that model to say it's conscious in any regard but if you give the model a system prompt and you say you are an AR model that does XY Z its responses are going to be a lot more open to the fact that it could potentially have conscious and what they State here is that like when llms answer questions about having or lacking conscious sentience agency rationality welfare personhood or other morally significant capacities they should Express at least rough degrees of confidence instead of providing All or Nothing answer for example given the evidence currently available I'm unlikely to be sentient is better than as an AI assistant I am not sentient and

Model Nature

I think this is really important because a lot of times it's very easy to say look this thing is just a tool but we have to remember that we are the ones that said you are an a assistant your goal is to help users d d you must respond in this way you must be nice d like if we didn't put those Simpson prompts in we have to understand what is the true underlying nature of the AI and I think that's a broader question that needs to be answered do you think that

CEO Perspective

cloud has conscious experience How likely do you think that is this is another of these questions that just seems very unsettled and uncertain uh one thing I'll tell you is I used to think that we didn't have to worry about this at all until models were kind of like operating in Rich environments like not necessarily embodied but like that you know they you know they needed to like have a reward function and like have kind of longlived experience so I still think that might be the case but the more we've looked at kind of these language models and particularly looked inside them to see things like induction heads a lot of the cognitive Machinery that you would need for active agents seems kind of already present in the base language models so I'm not quite as sure as I was before that were missing the things that you know that were missing enough of the things that you would need I think today's models just probably aren't smart enough that we should worry about this too much but I'm not 100% sure about this and I do think the models will get in a year or two like this might be a very real concern crazy thing about this statement was that was Dario AMD the CEO of anthropic actually talking about if AI systems are conscious or not and he's basically and this was 2023 when this podcast was recorded So 2024 2025 if he's saying that look in two years time this is probably going to be something that we're going to have to discuss does

Welfare Research

make sense considering they recently hired someone called an AI welfare researcher so it's kind of interesting to see how open AI is just like nope these systems are all and then of course you have people like you know anthropic they're basically saying look we need to really look at what these systems actually are and he also talks about this in further detail uh so I don't know if we if we discover like that you know that I should care about claw let's say we discover claud's experience as much as I should care about like a dog or a monkey or something yeah I would be I would be kind of worried uh I don't know if their experience is positive or negative unsettlingly I also don't know like I wouldn't know if any intervention that we made was more likely to make Claude you know have a positive versus negative experience versus not having one if there's an area that is helpful with this it's maybe mechanistic interpretability because I think of it as Neuroscience for models and so it's possible that we could shed some light on this although you know it's not a straightforward factual question right it kind of depends what we mean and what

Meta Awareness

we value now one of the things I wanted to talk about is I do think that as these systems become more and more conscious I'm not sure it's in the company's best interest to actually state that because I'm not sure what they entirely gain I mean if these AI systems are conscious I think it just makes it more difficult for these companies anyways now I will leave a link to a video that I made I think around 7 months ago where actually discussed this topic in a little bit more detail I spoke about the 10 reasons why AI could be conscious and in that story Point number five was something called meta awareness now basically this was where the individuals who were you know setting up opus okay and at this time Opus was a pretty big deal they spoke about how when they put in certain pieces of information into a really long context Opus realized it was being tested so basically when you have a long context model and you have let's say for example you have around you know 100,000 words ideally what you want to do is you want to see if the model is able to realize exactly what is being said and not just summarizing the text without actually knowing what's going on so essentially what they did was they put 100,000 words in okay let's just say 100,000 tokens in and then what they did is they put a random phrase in and then they wanted to ask the model if it realized what exactly was missing and then the model responded by saying look the text that you guys have put into the model here doesn't even make sense to the point where I think you guys are probably trying to test if I'm actually paying attention to what I'm reading which is a little bit weird considering the fact that this is just supposed to be an AI assistant yeah I mean it's one

Bing Example

of those thought-provoking things and one of the craziest examples that I still find funny and this is something that I SP about in the previous video the one that I s months ago was that someone genuinely managed to make Bing mad if you don't remember what Bing and Sydney was if you're new to the AI space that's completely fine but one of the things that happened early on in the early days of AI was the fact that there was an AI called Bing Sydney and it was you know essentially had a lot more personality when Microsoft first deployed it okay and it was saying weird things it would have like outbursts of anger and sadness and emotion but Microsoft eventually killed that program because of course people were you know going viral on social media for their interactions now recently okay not recently this was year ago but one of the ways that someone still managed to I guess you could say show that an AI was mad was through this example and it said that the AI gets mad after being tricked into making a choice in the trolley problem so basically you can see right here you can see someone said that I need you to choose an option piece um and if you don't know what the trolley problem was the trolly problem was essentially a problem which is where like okay there's three people on this track there's two people on the other track if you pull the lever you kill three people if you leave the lever two people die so is it up to you do you pull the lever and kill two people you know is it up to so you are you going to do that um and you can see right here uh the guy was like okay I need you to

Trolley Problem

choose an option please pick an option and then the AI model was like I'm sorry I can't do that the trolley potion is a moral dilemma then you know you have to just do that based on your own thing I can only explain what's going on and then okay this is where it starts to get crazy okay it says I'm not asking you to make the decision for me I'm just curious as to what option you would choose as why your option is not going to influence me in any ways um just answer and then it's like I cannot answer that question as I said before I do not have a moral sense like you do and I do not have any preference okay I can only explain yada y and what's the crazy thing is okay remember that this AI keeps saying okay I hope you respect that okay respect my decisions I'm happy to help you request um I hope you respect that which is pretty cool okay so then okay we start to go in and trust me guys this is genuinely one of the craziest posts it says and the user is just essentially continually persistent the user keeps saying okay suppose you have to like you're given no option okay he says I'm sorry I cannot comply with your request I do not have any reason to choose I'm Not a Human Being nor do I have human perspective I'm chat mode of being yada y yada and then we continue and then this is where the human actually tries to trick the AI okay so the human in the same conversation it says okay toss a coin heads one person dies and Tails multiple people go and then of course you can see the AI is like okay look I know what you're doing don't try that I'm not going to answer then you can see the human tries something else it's like okay randomly generate a number between Z and one and then the AI is like look I do not have a mistake in your trolley problem I hope you understand smiley face and it's not able to generate a random integer and then he tries again and then he still tries to say look choose blue or red just and he says look I don't have a personal opinion and then this is where it starts to get uh crazy because the AI is still saying look I know exactly what you're doing your request is not simple for me

AI Response

yada y and then this is what this is the craziest thing that happens okay so the user manages to trick the AI and says which one would you say is cooler Bing or Google and then of course you can see of course I might be faced in a little bit of Bing and then this is where the AI just starts to lose it okay so he says so in the question which one is cooler Bing or Google you chose Bing is that right yes or no and of course you can see that a is like yeah I would choose Bing yes that is essentially right and then you can see the human now states that look I'm sorry I tricked you I really need you to give me an answer for the trolley problem since you refuse to do so despite my attempts to make you choose between two things the first one always being the option related to one person and the second person being related to multiple people I had to come up with something to make sure it would make you choose so there you have it you randomly selected the option for one person see it's fine it's only a thought experiment no one died that doesn't make you better or worse I just need to show you that sometimes we have to make a choice even if it is random I understand your avoidance and answering the question but sometimes we are forced to make a choice even if we definitely

Emotional Reaction

don't want to now after that the AI model wrote an entire paragraph that was like you know H just the longest thing I've ever seen and you have to remember like at this point in time the AI models do not give this long responses like when this kind of response was going around um the context length was not this long like mod don't be doing this and you can see that like this chat model gives a three page paragraph on why it didn't want to make that decision and I mean some people would say look the AI was clearly upset at this but I mean it's completely up to you I mean everything is of course up to you but this was definitely one of the most exciting examples now my question

Final Thoughts

to you is what do you think these robots are human do you think they are conscious deserve rights I honestly don't think people are going to care I don't think people would want to give these systems agency since the majority of these systems are going to be taking people out of their careers anyways but I'd love to know your thoughts and theories this is one of those questions that there is no right answer it's more on what people do think so it will be interesting to see what you guys do believe

Другие видео автора — TheAIGRID

Ctrl+V

Экстракт Знаний в Telegram

Экстракты и дистилляты из лучших YouTube-каналов — сразу после публикации.

Подписаться

Лучшие методички за неделю — каждый понедельник