# Googles New AI Co Scientist Just Changed EVERYTHING (AI co-scientist Explained) ## Метаданные - **Канал:** TheAIGRID - **YouTube:** https://www.youtube.com/watch?v=P4V8zFaJsu0 - **Дата:** 21.02.2025 - **Длительность:** 12:39 - **Просмотры:** 60,060 ## Описание Join my AI Academy - https://www.skool.com/postagiprepardness 🐤 Follow Me on Twitter https://twitter.com/TheAiGrid 🌐 Checkout My website - https://theaigrid.com/ Links From Todays Video: https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/ 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 Music Used LEMMiNO - Cipher https://www.youtube.com/watch?v=b0q5PR1xpA0 CC BY-SA 4.0 LEMMiNO - Encounters https://www.youtube.com/watch?v=xdwWCl_5x2s #LLM #Largelanguagemodel #chatgpt #AI #ArtificialIntelligence #MachineLearning #DeepLearning #NeuralNetworks #Robotics #DataScience ## Содержание ### [0:00](https://www.youtube.com/watch?v=P4V8zFaJsu0) Segment 1 (00:00 - 05:00) So today we're going to be taking a look at something that has actually taken the industry by storm and that is of course Google's co- scientist I think this is a story that is remarkable in terms of what it's able to do and it gives us an indication as to where we are headed when we look at AI in terms of its ability to be able to help us achieve scientific discoveries and of course achieve efficiency in researching ways to effectively treat people so essentially the co- scientist is a multi-agent AI system developed by Google research and this is designed to help scientists generate new hypotheses and research proposal so basically what this does is it acts as a virtual collaborator which is capable of understanding complex topics and suggesting new research directions now this thing is pretty crazy because there have been some real world implications which I'll get into later but first we're going to dive into exactly how this works so you can see here in the short demo and I'm going to get into a little bit more of the details in a moment but you can see right here that we have the scientist so who is of course the person that would you know specify the research goal and then of course you would actually specify the research goal to the AI Co scientist which is you know made up of entirely sub agents so you've got a supervi agent a generation agent all of these agents and then of course you essentially have all those ideas and those ideas compete against one another and eventually you know you have the best one and then that one of course is proposed so how this works in terms of what each agent does the generation agent is going to be the one that creates new high hypotheses the reflection agent this is basically the agent that is going to be the one that evaluates and refines the ideas this is where you can see it has full review with web search so it's able to search the web it's able to do a simulation review a tournament review and deep verification so all of these things are really good for validating the idea then of course you've got the evolution agent which is basically something that you know improves the idea over time and gets inspiration from other ideas and then of course you also have the meta review agent this is where it ensures accuracy and scientific value and then of course we have a ranking agent and this is I think one of the most important thing because this prioritizes the best research directions so it says right here that the research hypotheses comparison and ranking with scientific debate in tournaments and basically it just continuously ranks the ideas and of course with the reflection with the evolution it basically over time and this thing actually utilizes test time compute so over time you get more and more ideas that are just continually better and essentially it just starts with of course the scientists basically just saying look this is you know where I'd want to research of course with constraints and other attributes so this is basically how the entire architecture is it shows the entire multi- aai agent framework with of course tool use search additional tools it also has memory and right here like I say you know continuously generates reviews debates and improves research hypotheses over time so this is something where you doesn't just you know put out one idea internally it's reviewing I don't actually have the number of ideas that it's actually reviewing but it's reviewing a number of different ideas evaluating those reflecting on those and ensuring it can then rank those and ensure it gets better over time or whilst browsing the web and ensuring that I can validate everything through scientific database to validate its findings and then this is where we have the further explanation on how the AI scientist passes the assigned goal into a research plan configuration managed by a supervisor agent the supervisor agent assigns the specialized agents to the work acue and allocates resources and this design enables this system to flexibly scale compute and iteratively improve scientific reasoning toward the specified research goal so you can see we got the supervisor agent here that actually assigns these agents to the workers and then of course this entire system is able to generate the research overview with the detailed hypotheses now one of the crazy things about this is that this research agent scientist agent workflow is something that actually utilizes test time compute so you can see right here they actually talk about how the AI co- scientist leverages test time compute scaling to iteratively reason evolve and improve outputs and this is something that's really crazy because we know that you know the test time compute Paradigm was something that only recently occurred and of course now we're already seeing that it has applications in many different fields you can see right here it says key reasoning steps include self-play based scientific debate for novel hypothesis generation ranking tournaments for hypothesis comparison and an evolution process for quality improvement says that the system's agentic nature facilitates recursive self-critique in including tool use for feedback to refine hypotheses and proposals so it seems that over time this is something that continually brings better ideas and I could probably bet that over time with even more compute and even you know a more efficient algorithm this system outputs better hypotheses you can also see that this system selfimprovement relies on the ELO Auto evaluation metric derived from its tournaments and basically in this context the tournaments refer to a competitive ranking process used by the AI cociena hypothesis the system basically generates multiple ideas then ### [5:00](https://www.youtube.com/watch?v=P4V8zFaJsu0&t=300s) Segment 2 (05:00 - 10:00) systematically compares the ideas using the predefined criteria and basically they just compare all of those ideas against each other and they look at the strength the weaknesses the supporting evidence and the best ideas are then ranked and then of course iteratively refined using a self-improvement loop and that of course ensures only the highest quality ideas are presented by the scientist and you can see right here it says we analyze the concordance between ELO ratings and of course the GP QA Benchmark on its Diamond set of challenging questions and we found that higher ELO ratings positively corate with a high probability of correct answers right here you can see the concordance of the ELO rating with the AI Co scientist performance on The gpq Diamond set questions you can see Gemini 2. 0 is a bit stagnant but the AI Co so you can see right here that seven domain experts curated 15 open research goals and the best guess Solutions in their field of expertise using the automated elom metric we observed that the AI co- scientist outperformed other state-of-the-art agentic and reasoning models for these complex problems so essentially this chart right here basically just shows how the AI co- scientists performs compared to the other AI models and human experts when coming up with new research ideas and basically scientists gave 15 different problems to both Ai and you know human experts and then they used an ELO rating system which is basically just the way you rank up performance like in chess to see who came up with the best Solutions and this graph basically shows that the AI cociena the more it worked on the problem of course test time compute now you can see right here where humans are you can see where the human expert is you can also see where Gemini 2. 0 flash 2 is we can also see that the AI co- scientist overall clearly surpasses them in all metrics so this is really good because of course this means that AI can keep improving the longer it works on a problem and it can help scientists find better Solutions faster so if you actually want to talk about the real world use cases because of course there are fancy demos and people are always like okay this is cool but how does that actually help us basically they did something on how AI is hoping to find new uses for existing drugs to treat acute myoid leukemia which is a type of blood cancer and normally creating new medicines takes a long time and costs a lot of money but drug repurposing means scientists find new ways to use medicines that we already have and Google's AI Co scientist was used to predict which existing drugs might help fight this type of cancer and basically after they tested the AI suggestions in a lab scientists found that one of the drugs called Kira 6 was able to you know as you can see right here reduce cancer cell growth at certain Doses and this graph shows how the drug concentration increases and the number of cancer cells decreases meaning it could be an effective treatment and this is because it means that AI can basically speed up cancer research helping doctors find better treatments faster and with fewer side effects so this is one of the real world use cases you know one of the examples that they showed you've also got another one here which is basically where um they did a study on liver fibrosis so this is basically liver fibrosis is basically where you have the liver getting too much scarring which makes it harder for it to work properly and scientists of course need new ways to stop this but figuring out what to Target is pretty tricky so Google's Ai cociena and scientists tested them in lab grown mini L called these organoids and essentially this graph right here shows the fibrosis inducer and this is you know of course what made scarring worse this the second bar the fibrosis inhibitor this helped reduce scarring and of course the last four bars which are the AI suggested drugs these also helped reduce scarring meaning that you know the AI might have actually found new treatments that actually work so you can see right here the first two ones actually did manage to make this go down a decent amount which is of course really good so this one is basically how AI helped ReDiscover a key mechanism in antimicrobial resistance which is basically how bacteria evolve to resist antibiotics so normally scientists would spend years on this so you know scientists you know basically spend years doing experiments to understand how bacteria share resistance genes and one key Discovery was of cfpi CIS which is basically small DNA segments that help bacteria to transfer resistance genes and here's exactly what happened so in the 2013 to 2025 humans slowly figured out how this actually worked through experiments but what's crazy is that in 2024 researchers asked the Google scientists the same question and in just two days the AI independently figured out that the CF pics interacted or interacts with the fages to spread the resistance so the crazy thing about this is that AI just matched humans years of research in literally just two days independently which is absolutely insane because it managed to basically figure out what took you know humans around you know seven years and it managed to do that in fact not even seven years in fact like a lot longer than that and I manag to do that in just 2 days so AI was able to do this very independently and it basically sped up the you know Discovery process from ### [10:00](https://www.youtube.com/watch?v=P4V8zFaJsu0&t=600s) Segment 3 (10:00 - 12:00) years to dat so you can imagine right like how crazy that is in terms of the development of drugs and when these individuals like Dario Amad was talking about the fact that you know scientific research is going to be sped up by tenfold this is the kind of thing that they were talking about even though some people were stating that they were just being hyperbolic with their claims but clearly this is one of the first times where you can actually see that literally the scientist was able to you know do this within 48 hours which is absolutely insane so one of the things I did want to look was of course you know was it just in the training data but you know looking at the image and you know the text carefully there's a few points that do indicate that this was a controlled test to verify that the AI wasn't just recalling the training data basically meaning that the AI didn't just remember this and then pretend and basically the you know they talk about how there was a third validation test where the researchers specifically chose a topic that had not yet been revealed in the public domain more specifically you know they took about how this was you know testing the AI co- scientist with an identical research question about work that only EX assisted in original novel laboratory experiments you know performed prior to the use of the AI co- scientist systems so this is something that is actually real is actually true and it's pretty crazy so we could actually see you know all of the kinds of research that we really do need speed up by tfold and I mean think about it like this guys this was just you know development of the AI co- scientist version one what happens when we have you know version 10 and we have a million of them running 247 guys running uh you know just so many different experiments what happens then think about it guys that's absolutely insane so that being said hopefully you guys did enjoy this video and I really did want to make a video on this because I think this is a Monumental piece of information that most people just didn't realize and let me know what you guys think about this because I do hope that all of The Chronic illnesses that people do suffer from all of the horrible debilitating disease that exist in the world can just eventually disappear and I think there's really you know potential to conquer many of the afflictions we still face right a lot of the easy ones like uh you know diseases that you know were addressed by sanitation or vaccination or antibiotics we've solved but things like cancer and Alzheimer's disease much more complicated and so I'm wondering if AI is really what we need to understand that complexity and to surmount those diseases frankly much faster than you know than I think most of us are imagining we're getting used to a world where those diseases are very hard to address and progress is very slow I don't think it needs to be that way I think if we get it right these you know incur diseases could actually we could actually overcome and you know we'll look back at them you know the way we look back at Bubonic plague or Ms thank you guys for watching the video and I'll see you in the next one --- *Источник: https://ekstraktznaniy.ru/video/13286*