Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing PaperQA2, the first AI agent that conducts entire scientific literature reviews on its own. PaperQA2 is also the first agent to beat PhD and Postdoc-level biology researchers on multiple literature research tasks, as measured both by accuracy on objective benchmarks and assessments by human experts. We are publishing... a paper and open-sourcing the code. This is the first example of AI agents exceeding human performance on a major portion of scientific research, and will be a game-changer for the way humans interact with the scientific literature. Paper and code are below, and congratulations in particular to Michael Skarlinski, Sam Cox, Jon Laurent, James Braza, Michaela Hinks, Michael Hammerling, Manvitha Ponnapati, Andrew White 🐦‍⬛, and others who pulled this off. 1/show more

Sam Rodriques

21,364 subscribers

555,733 views • 1 year ago •via X (Twitter)

Health & Wellness Education Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

Sam Rodriques1 year ago

PaperQA2 finds and summarizes relevant literature, refines its search parameters based on what it finds, and provides cited, factually grounded answers that are more accurate on average than answers provided by PhD and postdoc-level biologists. When applied to answer highly specific questions, like this one, it obtains SOTA performance on LitQA2, part of LAB-Bench focused on information retrieval. 2/

Sam Rodriques1 year ago

PaperQA2 can also do broad-based literature reviews. WikiCrow, which is an agent based on PaperQA2, writes Wikipedia-style articles that are significantly more accurate on average than actual human-written articles on Wikipedia, as judged by PhD and postdoc-level biologists. We are using WikiCrow to write updated summaries of all 20,000 genes in the human genome. They are still being written, but in the meantime see a preview: 3/

Sam Rodriques1 year ago

We spent a lot of effort on making our open source version be excellent. We put together a new system of building metadata of arbitrary PDFs, full-text search, and more. See it here: 4/

Sam Rodriques1 year ago

Also, see our preprint for details, here: 5/

Sam Rodriques1 year ago

And, of course, this was all made possible through the wonderful generosity of Eric and Wendy Schmidt, and all of our other funders, including Open Philanthropy for supporting our work on LitQA2, the NSF National AI Resource program, and others! 6/

Ben Blaiszik1 year ago

This is great work @SGRodriques! If I understand this correctly, the open source version requires downloaded pdfs in the folder structure. Just imagine what you could achieve if there was easy programmatic access to all publications and precomputed embeddings. Can someone just buy out the journal rights? :)

Postholer - GIS Resources1 year ago

"Exceeding human performance" which translates into "still has errors". Using lossy techniques like AI are fine for art, music, etc. For subject matter that must be absolute, lossy techniques will not work. Compress your perfect data in a lossy compression format, uncompress it, and you have AI equivalent results.

Brendon Burchard1 year ago

Can you load it up with the 1000 most cited studies in psychology then put on an open url so we can ask it questions

Vincent Weisser1 year ago

Awesome work Sam and team!!

Mike Nolivos1 year ago

@Plinz Massive respect to you and team! This is incredibly important and thank you for open sourcing 🙏

Related Videos

Systematic literature reviews take 12-18 months to complete. Looks like AI is going to fully automate systematic reviews sooner than later. SciSpace ( SciSpace) just launched an autonomous AI agent that conducts a systematic literature review with a single prompt. Go to scispace[.]com and run the following prompt: "Conduct a systematic literature review on [your topic]" SciSpace agent will generate research questions based on the PICO framework. You can review these questions and edit them according to your specific requirements. The agent will also draft screening criteria that you can edit according to your needs. Then the agent asks you to select the databases you want to use and the date range for paper. After this step, everything is fully automated. The agent will search for papers in the relevant databases, it will combine and rerank the papers. Then it will start the title and abstract screening and include the papers that meet the include criteria. In the next step, it will download the full text of included papers and screen them followed by data extraction. Based on the extracted data, it generates a complete systematic literature review and also a PRISMA diagram. It will also give you a table of papers included along with the rational for including them. The only thing that is keeping AI agents to fully automate systematic literature reviews fields is the papers behind paywalls. Check out the agent at scispace[.]com and see if you find its review useful.

Systematic literature reviews take 12-18 months to complete. Looks like AI is going to fully automate systematic reviews sooner than later. SciSpace ( SciSpace) just launched an autonomous AI agent that conducts a systematic literature review with a single prompt. Go to scispace[.]com and run the following prompt: "Conduct a systematic literature review on [your topic]" SciSpace agent will generate research questions based on the PICO framework. You can review these questions and edit them according to your specific requirements. The agent will also draft screening criteria that you can edit according to your needs. Then the agent asks you to select the databases you want to use and the date range for paper. After this step, everything is fully automated. The agent will search for papers in the relevant databases, it will combine and rerank the papers. Then it will start the title and abstract screening and include the papers that meet the include criteria. In the next step, it will download the full text of included papers and screen them followed by data extraction. Based on the extracted data, it generates a complete systematic literature review and also a PRISMA diagram. It will also give you a table of papers included along with the rational for including them. The only thing that is keeping AI agents to fully automate systematic literature reviews fields is the papers behind paywalls. Check out the agent at scispace[.]com and see if you find its review useful.

Mushtaq Bilal, PhD

41,511 views • 3 months ago

Today, we are launching the first publicly available AI Scientist, via the FutureHouse Platform. Our AI Scientist agents can perform a wide variety of scientific tasks better than humans. By chaining them together, we've already started to discover new biology really fast. With the platform, we are bringing these capabilities to the wider community. Watch our long-form video, in the comments below, to learn more about how the platform works and how you can use it to make new discoveries, and go to our website or see the comments below to access the platform. We are releasing three superhuman AI Scientist agents today, each with their own specialization: A general-purpose agent (Crow); An agent to automate literature reviews (Falcon); and An agent to answer the question “Has anyone done X before” (Owl). We are also releasing an experimental agent, Phoenix, that has access to a wide variety of tools for planning experiments in chemistry. More on that below. The three literature search agents (Crow, Falcon, and Owl) have benchmarked superhuman performance. They also have access to a large corpus of full scientific texts, which means that you can ask them more detailed questions about experimental protocols and study limitations that general-purpose web search agents, which usually only have access to abstracts, might miss. Our agents also use a variety of factors to distinguish source quality, so that they don’t end up relying on low-quality papers or pop-science sources. Finally, and critically, we have an API, which is intended to allow researchers to integrate our agents into their workflows. Phoenix is an experimental project we put together recently just to demonstrate what can happen if you give the agents access to lots of scientific tools. It is not better than humans at planning experiments yet, and it makes a lot more mistakes than Crow, Falcon, or Owl. We want to see all the ways you can break it! The agents we are releasing today cannot yet do all (or even most!) aspects of scientific research autonomously. However, as we show in the video, you can already use them to generate and evaluate new hypotheses and plan new experiments way faster than before. Internally, we also have dedicated agents for data analysis, hypothesis generation, protein engineering, and more, and we plan to launch these on the platform in the coming months as well. Within a year or two, it is easy to imagine that the vast majority of desk work that scientists do today will be accelerated with the help of AI agents like the ones we are releasing today. The platform is currently free-to-use. Over time, depending on how people use it, we may implement pricing plans. If you want higher rate limits, especially for research projects, get in touch. Michael Skarlinski, Andrew White 🐦‍⬛, Tyler Nadolski, Remo Storni, James Braza, Ludovico Mitchener, Michaela Hinks, as well as Jason Carman and his team for making such fantastic videos of us!

Today, we are launching the first publicly available AI Scientist, via the FutureHouse Platform. Our AI Scientist agents can perform a wide variety of scientific tasks better than humans. By chaining them together, we've already started to discover new biology really fast. With the platform, we are bringing these capabilities to the wider community. Watch our long-form video, in the comments below, to learn more about how the platform works and how you can use it to make new discoveries, and go to our website or see the comments below to access the platform. We are releasing three superhuman AI Scientist agents today, each with their own specialization: A general-purpose agent (Crow); An agent to automate literature reviews (Falcon); and An agent to answer the question “Has anyone done X before” (Owl). We are also releasing an experimental agent, Phoenix, that has access to a wide variety of tools for planning experiments in chemistry. More on that below. The three literature search agents (Crow, Falcon, and Owl) have benchmarked superhuman performance. They also have access to a large corpus of full scientific texts, which means that you can ask them more detailed questions about experimental protocols and study limitations that general-purpose web search agents, which usually only have access to abstracts, might miss. Our agents also use a variety of factors to distinguish source quality, so that they don’t end up relying on low-quality papers or pop-science sources. Finally, and critically, we have an API, which is intended to allow researchers to integrate our agents into their workflows. Phoenix is an experimental project we put together recently just to demonstrate what can happen if you give the agents access to lots of scientific tools. It is not better than humans at planning experiments yet, and it makes a lot more mistakes than Crow, Falcon, or Owl. We want to see all the ways you can break it! The agents we are releasing today cannot yet do all (or even most!) aspects of scientific research autonomously. However, as we show in the video, you can already use them to generate and evaluate new hypotheses and plan new experiments way faster than before. Internally, we also have dedicated agents for data analysis, hypothesis generation, protein engineering, and more, and we plan to launch these on the platform in the coming months as well. Within a year or two, it is easy to imagine that the vast majority of desk work that scientists do today will be accelerated with the help of AI agents like the ones we are releasing today. The platform is currently free-to-use. Over time, depending on how people use it, we may implement pricing plans. If you want higher rate limits, especially for research projects, get in touch. Michael Skarlinski, Andrew White 🐦‍⬛, Tyler Nadolski, Remo Storni, James Braza, Ludovico Mitchener, Michaela Hinks, as well as Jason Carman and his team for making such fantastic videos of us!

Sam Rodriques

724,665 views • 1 year ago

Introducing Multiverse: the first AI-generated multiplayer game. Multiplayer was the missing piece in AI-generated worlds — now it’s here. Players can interact and shape a shared AI-simulated world, in real-time. Training and research cost < $1.5K. Run it on your own PC. We are open-sourcing everything: code, data, weights, architecture, and research. Here’s a closer look (and how it works!):

Introducing Multiverse: the first AI-generated multiplayer game. Multiplayer was the missing piece in AI-generated worlds — now it’s here. Players can interact and shape a shared AI-simulated world, in real-time. Training and research cost < $1.5K. Run it on your own PC. We are open-sourcing everything: code, data, weights, architecture, and research. Here’s a closer look (and how it works!):

Jonathan Jacobi

386,462 views • 1 year ago

This AI agent just surpassed humans for the first time ever Simular open-sourced Agent S, and scored 72.6% on OSWorld bench vs 72.36% humans, automating your desktop and complex workflows 6 wild examples + how to try: 1. Turn research paper to X thread with assets

This AI agent just surpassed humans for the first time ever Simular open-sourced Agent S, and scored 72.6% on OSWorld bench vs 72.36% humans, automating your desktop and complex workflows 6 wild examples + how to try: 1. Turn research paper to X thread with assets

Alvaro Cintas

25,438 views • 6 months ago

Today, we’re announcing the first major discovery made by our AI Scientist with the lab in the loop: a promising new treatment for dry AMD, a major cause of blindness. Our agents generated the hypotheses, designed the experiments, analyzed the data, iterated, even made figures for the paper. The resulting manuscript is a first-of-a-kind in the natural sciences, in which everything that needed to be done to write the paper was done by AI agents, apart from actually conducting the physical experiments in the lab and writing the final manuscript. We are also introducing Robin, the first multi-agent system that fully automates the in-silico components of scientific discovery, which made this discovery. This is the first time that we are aware of that hypothesis generation, experimentation, and data analysis have been joined up in closed loop, and is the beginning of a massive acceleration in the pace of scientific discovery that will be driven by these agents. We will be open-sourcing the code and data next week. Robin is a multi-agent system that uses Crow, Falcon, and Finch, the agents on our platform, to generate novel hypotheses, plan experiments, and analyze data. We asked Robin to find a new treatment for dry age-related macular degeneration. Robin considered the disease mechanisms associated with dry AMD, proposed a specific experimental assay that could be used to evaluate hypotheses in the wet lab, and proposed specific molecules we could test in that assay. We tested the molecules and gave it the resulting data, which it analyzed before proposing more experiments. In the end, it identified Ripasudil, a Rho Kinase inhibitor (ROCK inhibitor) that is approved in Japan for several other diseases, which seems very promising as potential treatment for dry AMD. It also identified specific molecular mechanisms that might underlie the effects of Ripasudil in RPE cells, from an RNA sequencing experiment it proposed. To be clear, no one has proposed using ROCK inhibitors to treat dry AMD in the literature before, as far as we can find, and I think it would have been very difficult for us to come up with this hypothesis without the agents. We have also run the proposed treatment by several experts in AMD, who confirm that it is interesting and novel. Moreover, this project was fast: with Robin in hand, the entire project took about 10 weeks, which is way shorter than it would have taken if we had been doing all of the in-silico components ourselves. Important caveats: We are real biologists at FutureHouse, so I want to be clear that although the discovery here is exciting, we are not claiming that we have cured dry AMD. Fully validating this hypothesis as a treatment for dry AMD will take human trials, which will take much longer. Also, this discovery is cool, but it is not yet a "move 37"-style discovery. At the current rate of progress, I'm sure we will get to that level soon. Congratulations to the team. Congratulations in particular to Robin, which generated the hypotheses, proposed the experiments, analyzed the data and generated the figures. And major congratulations also to the human team, which built Robin: Michaela Hinks, Ali Ghareeb, Benjamin Chang, Ludovico Mitchener, Mo Razzak, Kiki Szostkiewicz, and Angela Yiu.

Today, we’re announcing the first major discovery made by our AI Scientist with the lab in the loop: a promising new treatment for dry AMD, a major cause of blindness. Our agents generated the hypotheses, designed the experiments, analyzed the data, iterated, even made figures for the paper. The resulting manuscript is a first-of-a-kind in the natural sciences, in which everything that needed to be done to write the paper was done by AI agents, apart from actually conducting the physical experiments in the lab and writing the final manuscript. We are also introducing Robin, the first multi-agent system that fully automates the in-silico components of scientific discovery, which made this discovery. This is the first time that we are aware of that hypothesis generation, experimentation, and data analysis have been joined up in closed loop, and is the beginning of a massive acceleration in the pace of scientific discovery that will be driven by these agents. We will be open-sourcing the code and data next week. Robin is a multi-agent system that uses Crow, Falcon, and Finch, the agents on our platform, to generate novel hypotheses, plan experiments, and analyze data. We asked Robin to find a new treatment for dry age-related macular degeneration. Robin considered the disease mechanisms associated with dry AMD, proposed a specific experimental assay that could be used to evaluate hypotheses in the wet lab, and proposed specific molecules we could test in that assay. We tested the molecules and gave it the resulting data, which it analyzed before proposing more experiments. In the end, it identified Ripasudil, a Rho Kinase inhibitor (ROCK inhibitor) that is approved in Japan for several other diseases, which seems very promising as potential treatment for dry AMD. It also identified specific molecular mechanisms that might underlie the effects of Ripasudil in RPE cells, from an RNA sequencing experiment it proposed. To be clear, no one has proposed using ROCK inhibitors to treat dry AMD in the literature before, as far as we can find, and I think it would have been very difficult for us to come up with this hypothesis without the agents. We have also run the proposed treatment by several experts in AMD, who confirm that it is interesting and novel. Moreover, this project was fast: with Robin in hand, the entire project took about 10 weeks, which is way shorter than it would have taken if we had been doing all of the in-silico components ourselves. Important caveats: We are real biologists at FutureHouse, so I want to be clear that although the discovery here is exciting, we are not claiming that we have cured dry AMD. Fully validating this hypothesis as a treatment for dry AMD will take human trials, which will take much longer. Also, this discovery is cool, but it is not yet a "move 37"-style discovery. At the current rate of progress, I'm sure we will get to that level soon. Congratulations to the team. Congratulations in particular to Robin, which generated the hypotheses, proposed the experiments, analyzed the data and generated the figures. And major congratulations also to the human team, which built Robin: Michaela Hinks, Ali Ghareeb, Benjamin Chang, Ludovico Mitchener, Mo Razzak, Kiki Szostkiewicz, and Angela Yiu.

Sam Rodriques

1,106,937 views • 1 year ago

We’re entering the 10x speed of research publication workflow with AI. SciSpace (SciSpace), the first AI Agent built exclusively for the scientific community, is releasing so many inredibly useful features. 🎯 This is the AI Agent that can use 150+ tools, 59 databases, and 280M+ papers A few weeks back they launched BioMed Agent - It can design entire molecular biology workflows and even create publication-ready illustrations in a single prompt. This is its new domain-specialized AI co-scientist that sits on top of the existing SciSpace Agent and automates full biomedical workflows, from raw data and papers to analysis, decisions, and the final production-grade illustrations. You just need to give it 1 prompt. And today the added the following - Library Search, so it can search and analyze the PDFs already sitting in My Library, letting people ask questions across their own paper pile while keeping it private. - Now connects directly to Zotero, so the Agent can pull and work with the papers you already saved there without manual uploads. - For bigger prompts, it auto-triggers a Report Writing Sub-Agent that turns the chat into a structured research-style report, which is way cleaner for literature reviews and long summaries. - And when you get something worth keeping, Save to Notebook lets you store the output as .md notes with citations in My notebooks, so the work becomes reusable research notes instead of disappearing into chat. Behind the scenes, it indexes the PDF text, pulls a few relevant chunks for the question, then writes an answer grounded on those chunks.

We’re entering the 10x speed of research publication workflow with AI. SciSpace (SciSpace), the first AI Agent built exclusively for the scientific community, is releasing so many inredibly useful features. 🎯 This is the AI Agent that can use 150+ tools, 59 databases, and 280M+ papers A few weeks back they launched BioMed Agent - It can design entire molecular biology workflows and even create publication-ready illustrations in a single prompt. This is its new domain-specialized AI co-scientist that sits on top of the existing SciSpace Agent and automates full biomedical workflows, from raw data and papers to analysis, decisions, and the final production-grade illustrations. You just need to give it 1 prompt. And today the added the following - Library Search, so it can search and analyze the PDFs already sitting in My Library, letting people ask questions across their own paper pile while keeping it private. - Now connects directly to Zotero, so the Agent can pull and work with the papers you already saved there without manual uploads. - For bigger prompts, it auto-triggers a Report Writing Sub-Agent that turns the chat into a structured research-style report, which is way cleaner for literature reviews and long summaries. - And when you get something worth keeping, Save to Notebook lets you store the output as .md notes with citations in My notebooks, so the work becomes reusable research notes instead of disappearing into chat. Behind the scenes, it indexes the PDF text, pulls a few relevant chunks for the question, then writes an answer grounded on those chunks.

Rohan Paul

11,574 views • 5 months ago

No one country can deal with #AI on its own. The AI Scientific Panel is calling for a multilateral solution to AI governance — one that shares the benefits of AI equally. The Panel will present its first report at the Global Dialogue on AI Governance in Geneva on 6 and 7 July.

No one country can deal with #AI on its own. The AI Scientific Panel is calling for a multilateral solution to AI governance — one that shares the benefits of AI equally. The Panel will present its first report at the Global Dialogue on AI Governance in Geneva on 6 and 7 July.

United Nations Geneva

18,821 views • 12 days ago

Today, we’re announcing Kosmos, our newest AI Scientist, available to use now. Users estimate Kosmos does 6 months of work in a single day. One run can read 1,500 papers and write 42,000 lines of code. At least 79% of its findings are reproducible. Kosmos has made 7 discoveries so far, which we are releasing today, in areas ranging from neuroscience to material science and clinical genetics, in collaboration with our academic beta testers. Three of these discoveries reproduced unpublished findings; four are net new, validated contributions to the scientific literature. AI-accelerated science is here. Our core innovation in Kosmos is the use of a structured, continuously-updated world model. As described in our technical report, Kosmos’ world model allows it to process orders of magnitude more information than could fit into the context of even the longest-context language models, allowing it to synthesize more information and pursue coherent goals over longer time horizons than Robin or any of our other prior agents. In this respect, we believe Kosmos is the most compute-intensive language agent released so far in any field, and by far the most capable AI Scientist available today. The use of a persistent world model also enables single Kosmos trajectories to produce highly complex outputs that require multiple significant logical leaps. As with all of our systems, Kosmos is designed with transparency and verifiability in mind: every conclusion in a Kosmos report can be traced through our platform to the specific lines of code or the specific passages in the scientific literature that inspired it, ensuring that Kosmos’ findings are fully auditable at all times. We are also using this opportunity to announce the launch of Edison Scientific, a new commercial spinout of FutureHouse, which will be focused on commercializing our agents and applying them to automate scientific research in drug discovery and beyond. Edison will be taking over management of the FutureHouse platform, where you can access Kosmos alongside our Literature, Molecules, and Precedent agents (previously Crow, Phoenix, and Owl). Edison will continue to offer free tier usage for casual users and academics, while also offering higher rate limits and additional features for users who need them. You can read more about this spinout on our blog, below. A few important notes if you’re going to try Kosmos. Firstly, Kosmos is different from many other AI tools you might have played with, including our other agents. It is more similar to a Deep Research tool than it is to a chatbot: it takes some time to figure out how to prompt it effectively, and we have tried to include guidelines on this to help (see below). It costs $200/run right now (200 credits per run, and $1/credit), with some free tier usage for academics. This is heavily discounted; people who sign up for Founding Subscriptions now can lock in the $1/credit price indefinitely, but the price ultimately will probably be higher. Again, this is less chatbot and more research tool, something you run on high-value targets as needed. Some caveats are also warranted. Firstly, we find that 80% of Kosmos findings are reproducible, which also means 20% are not -- some things it says will be wrong. Also, Kosmos certainly does produce outputs that are the equivalent to several months of human labor, but it also often goes down rabbit holes or chases statistically significant yet scientifically irrelevant findings. We often run Kosmos multiple times on the same objective in order to sample the various research avenues it can take. There are still a bunch of rough edges on the UI and such, which we are working on. Finally, we are aware that the 6 month figure is much greater than estimates by other AI labs, like METR, about the length of tasks that AI Agents can currently perform. You can read discussion about this in our blog post. Huge congratulations to our team that put this together, led by Ludovico Mitchener and Michaela Hinks: Angela Yiu, Benjamin Chang, Sid Narayanan, Edwin Melville-Green, Albert Bou, Arvis Sulovari, Oz Wassie, Jon Laurent. A particular shout out to Michael Skarlinski and his team that rebuilt the platform for this launch, especially Andy Cai Andy Cai, Richard Magness, Remo Storni, Tyler Nadolski Tyler Nadolski, Mayk Caldas Mayk Caldas, Sam Cox Sam Cox and more. This work would not have been possible without significant contributions from academic collaborators Mathieu Bourdenx, Eric Landsness, Dániel Barabási, Nicky Evans, Tonio Buonassisi, Bruna Gomes, Shriya Reddy, Martha Foiani, and Randall Bateman. We also want to thank our numerous supporters, especially Eric Schmidt, who has been a tremendous ally. We will have more to say about our supporters soon!

Today, we’re announcing Kosmos, our newest AI Scientist, available to use now. Users estimate Kosmos does 6 months of work in a single day. One run can read 1,500 papers and write 42,000 lines of code. At least 79% of its findings are reproducible. Kosmos has made 7 discoveries so far, which we are releasing today, in areas ranging from neuroscience to material science and clinical genetics, in collaboration with our academic beta testers. Three of these discoveries reproduced unpublished findings; four are net new, validated contributions to the scientific literature. AI-accelerated science is here. Our core innovation in Kosmos is the use of a structured, continuously-updated world model. As described in our technical report, Kosmos’ world model allows it to process orders of magnitude more information than could fit into the context of even the longest-context language models, allowing it to synthesize more information and pursue coherent goals over longer time horizons than Robin or any of our other prior agents. In this respect, we believe Kosmos is the most compute-intensive language agent released so far in any field, and by far the most capable AI Scientist available today. The use of a persistent world model also enables single Kosmos trajectories to produce highly complex outputs that require multiple significant logical leaps. As with all of our systems, Kosmos is designed with transparency and verifiability in mind: every conclusion in a Kosmos report can be traced through our platform to the specific lines of code or the specific passages in the scientific literature that inspired it, ensuring that Kosmos’ findings are fully auditable at all times. We are also using this opportunity to announce the launch of Edison Scientific, a new commercial spinout of FutureHouse, which will be focused on commercializing our agents and applying them to automate scientific research in drug discovery and beyond. Edison will be taking over management of the FutureHouse platform, where you can access Kosmos alongside our Literature, Molecules, and Precedent agents (previously Crow, Phoenix, and Owl). Edison will continue to offer free tier usage for casual users and academics, while also offering higher rate limits and additional features for users who need them. You can read more about this spinout on our blog, below. A few important notes if you’re going to try Kosmos. Firstly, Kosmos is different from many other AI tools you might have played with, including our other agents. It is more similar to a Deep Research tool than it is to a chatbot: it takes some time to figure out how to prompt it effectively, and we have tried to include guidelines on this to help (see below). It costs $200/run right now (200 credits per run, and $1/credit), with some free tier usage for academics. This is heavily discounted; people who sign up for Founding Subscriptions now can lock in the $1/credit price indefinitely, but the price ultimately will probably be higher. Again, this is less chatbot and more research tool, something you run on high-value targets as needed. Some caveats are also warranted. Firstly, we find that 80% of Kosmos findings are reproducible, which also means 20% are not -- some things it says will be wrong. Also, Kosmos certainly does produce outputs that are the equivalent to several months of human labor, but it also often goes down rabbit holes or chases statistically significant yet scientifically irrelevant findings. We often run Kosmos multiple times on the same objective in order to sample the various research avenues it can take. There are still a bunch of rough edges on the UI and such, which we are working on. Finally, we are aware that the 6 month figure is much greater than estimates by other AI labs, like METR, about the length of tasks that AI Agents can currently perform. You can read discussion about this in our blog post. Huge congratulations to our team that put this together, led by Ludovico Mitchener and Michaela Hinks: Angela Yiu, Benjamin Chang, Sid Narayanan, Edwin Melville-Green, Albert Bou, Arvis Sulovari, Oz Wassie, Jon Laurent. A particular shout out to Michael Skarlinski and his team that rebuilt the platform for this launch, especially Andy Cai Andy Cai, Richard Magness, Remo Storni, Tyler Nadolski Tyler Nadolski, Mayk Caldas Mayk Caldas, Sam Cox Sam Cox and more. This work would not have been possible without significant contributions from academic collaborators Mathieu Bourdenx, Eric Landsness, Dániel Barabási, Nicky Evans, Tonio Buonassisi, Bruna Gomes, Shriya Reddy, Martha Foiani, and Randall Bateman. We also want to thank our numerous supporters, especially Eric Schmidt, who has been a tremendous ally. We will have more to say about our supporters soon!

Sam Rodriques

731,941 views • 8 months ago

Can #AI not only support but actually drive the future of scientific discovery? We are excited to introduce SciAgents💡🔬, an agentic AI aimed towards scientific discovery through the integration of large-scale knowledge graphs, LLMs, and adversarial interactions between multiple experts. The model is capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data, while retrieving new data via literature search. Using graph reasoning, SciAgents identifies interdisciplinary relationships that might otherwise remain hidden, offering a step-by-step strategy for discovery & innovation. The video features an audiotrack generated using 🍓#o1 based on the original paper and design examples, providing an explanation of the work and its implications. Key elements include: 1⃣Ontological Knowledge Graphs: Structuring and connecting scientific concepts to highlight relationships across fields. 2⃣Multi-Agent Collaboration: AI agents autonomously generate and refine hypotheses, critique research, and evaluate emerging trends. 3⃣Graph-Based Reasoning: Identifying novel material designs, such as mycelium-based composites or silk-pigment blends, informed by both natural and artificial patterns. SciAgents can be used as an autonomous or collaborative tool to assist human researchers. The system offers a more powerful way to process vast data, providing innovative paths to explore nature-inspired designs or unexpected material properties. In the field of materials science, for instance, SciAgents has already demonstrated how principles from biology, music, and art can converge to create new biomimetic materials. Through isomorphic mapping, parallels have been drawn between Beethoven’s 9th Symphony and biological structures, pointing to a broader applicability of AI-driven insights across disciplines. This project allows us to enhance capabilities of researchers, allowing them to explore larger datasets and propose hypotheses grounded in a vast, interconnected web of knowledge. The agentic system was built using @pyautogen #AI #ScientificResearch #GraphReasoning #AI4Science #MaterialsScience #InterdisciplinaryResearch #SciAgents #OpenAI Chi Wang

Can #AI not only support but actually drive the future of scientific discovery? We are excited to introduce SciAgents💡🔬, an agentic AI aimed towards scientific discovery through the integration of large-scale knowledge graphs, LLMs, and adversarial interactions between multiple experts. The model is capable of autonomously advancing scientific understanding by exploring novel domains, identifying complex patterns, and uncovering previously unseen connections in vast scientific data, while retrieving new data via literature search. Using graph reasoning, SciAgents identifies interdisciplinary relationships that might otherwise remain hidden, offering a step-by-step strategy for discovery & innovation. The video features an audiotrack generated using 🍓#o1 based on the original paper and design examples, providing an explanation of the work and its implications. Key elements include: 1⃣Ontological Knowledge Graphs: Structuring and connecting scientific concepts to highlight relationships across fields. 2⃣Multi-Agent Collaboration: AI agents autonomously generate and refine hypotheses, critique research, and evaluate emerging trends. 3⃣Graph-Based Reasoning: Identifying novel material designs, such as mycelium-based composites or silk-pigment blends, informed by both natural and artificial patterns. SciAgents can be used as an autonomous or collaborative tool to assist human researchers. The system offers a more powerful way to process vast data, providing innovative paths to explore nature-inspired designs or unexpected material properties. In the field of materials science, for instance, SciAgents has already demonstrated how principles from biology, music, and art can converge to create new biomimetic materials. Through isomorphic mapping, parallels have been drawn between Beethoven’s 9th Symphony and biological structures, pointing to a broader applicability of AI-driven insights across disciplines. This project allows us to enhance capabilities of researchers, allowing them to explore larger datasets and propose hypotheses grounded in a vast, interconnected web of knowledge. The agentic system was built using @pyautogen #AI #ScientificResearch #GraphReasoning #AI4Science #MaterialsScience #InterdisciplinaryResearch #SciAgents #OpenAI Chi Wang

Markus J. Buehler

208,378 views • 1 year ago

Excited to launch "Novix"🚀, our PhD-level AI-Scientist designed for autonomous scientific discovery. Novix revolutionizes research workflows through comprehensive capabilities spanning: deep research, innovative ideation, intelligent coding, advanced data analysis, automated experimentation, and paper writing. 🌐 Platform Access: 👉 Open-Source Foundation: 🚀 Accelerated Scientific Discovery Pipeline: From concept to publication-ready research with unprecedented efficiency ✨ Core Capabilities: - 🧠 Research Co-Pilot Intelligence: AI-powered ideation and hypothesis generation that collaborates with your research intuition - ⚙️ Autonomous Algorithm Innovation: End-to-end design, implementation, and validation of novel computational approaches - 📊 Intelligent Data Orchestration: Advanced analytics with automated insights discovery and compelling visualizations - 🔬 Scientific Reproducibility Engine: Automated verification and replication of research methodologies and findings - 📚 AI-Powered Deep Survey: Comprehensive literature synthesis and gap analysis across scientific domains We're building an AGI Level 4 innovation engine that empowers researchers, developers, and businesses to achieve breakthrough results in scientific innovation and discovery. From our open-source foundation to this production-ready platform, Novix represents a paradigm shift in how we reshape scientific discovery. 🎁 Launch Benefits - 🚪 Barrier-Free Access: Simply register and start exploring - 💰 Welcome Bonus: New users receive $5 in credits to experience the platform's full potential - 🎯 Enhanced Experience: Complete our user feedback survey to unlock a $20 Pro account with complete feature access We deeply understand the challenges of research work and genuinely hope Novix can serve as your trusted research companion. Join us in this exciting journey of AI-powered scientific discovery and help shape the future of research innovation!

Excited to launch "Novix"🚀, our PhD-level AI-Scientist designed for autonomous scientific discovery. Novix revolutionizes research workflows through comprehensive capabilities spanning: deep research, innovative ideation, intelligent coding, advanced data analysis, automated experimentation, and paper writing. 🌐 Platform Access: 👉 Open-Source Foundation: 🚀 Accelerated Scientific Discovery Pipeline: From concept to publication-ready research with unprecedented efficiency ✨ Core Capabilities: - 🧠 Research Co-Pilot Intelligence: AI-powered ideation and hypothesis generation that collaborates with your research intuition - ⚙️ Autonomous Algorithm Innovation: End-to-end design, implementation, and validation of novel computational approaches - 📊 Intelligent Data Orchestration: Advanced analytics with automated insights discovery and compelling visualizations - 🔬 Scientific Reproducibility Engine: Automated verification and replication of research methodologies and findings - 📚 AI-Powered Deep Survey: Comprehensive literature synthesis and gap analysis across scientific domains We're building an AGI Level 4 innovation engine that empowers researchers, developers, and businesses to achieve breakthrough results in scientific innovation and discovery. From our open-source foundation to this production-ready platform, Novix represents a paradigm shift in how we reshape scientific discovery. 🎁 Launch Benefits - 🚪 Barrier-Free Access: Simply register and start exploring - 💰 Welcome Bonus: New users receive $5 in credits to experience the platform's full potential - 🎯 Enhanced Experience: Complete our user feedback survey to unlock a $20 Pro account with complete feature access We deeply understand the challenges of research work and genuinely hope Novix can serve as your trusted research companion. Join us in this exciting journey of AI-powered scientific discovery and help shape the future of research innovation!

Chao Huang

16,854 views • 10 months ago

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Super excited to share 🧠MLGym 🦾 – the first Gym environment for AI Research Agents 🤖🔬 We introduce MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. The key contributions of our work are: 🕹️ Enables the exploration of different training algorithms for AI Research Agents such as RL 🛠️ Provides a flexible evaluation framework that can accommodate different artifacts such as models, algorithms, or predictions 🤖 Allows researchers to evaluate any model without the need to develop a custom agentic harness 🎯 Introduces 13 diverse open-ended AI Research tasks for evaluating AI Research Agents on a wide range of domains such as computer vision, natural language processing, reinforcement learning, game theory, and logical reasoning. 📈 Proposes a new evaluation metric for AI Research Agents MLGym makes it easy to: 1) Add new tasks 2) Evaluate new models 3) Integrate new agents Check out a video of the MLGym Agent to see how it performs the full pipeline of idea generation💡, implementation 👩‍💻, experimentation 👩‍🔬, and iteration 🔄 to improve on ML tasks. Huge thanks to the exceptionally talented Deepak Nathani who led this work and to all the other amazing collaborators who made this possible 🙏🫶🚀

Roberta Raileanu

104,982 views • 1 year ago

The safety of our people and the future of our society depend not only on infrastructure, but also on strong institutions, innovation, and knowledge. The commissioning of the Centre for DNA Forensics and Criminal Investigation, the first of its kind in Africa, is a major step in that direction. This facility will strengthen criminal investigations, support scientific research, train future experts, and enhance our ability to use modern forensic science to keep our communities safer. It is an investment in justice, security, and the kind of future we are building for generations to come. 𝗧𝗼𝗺𝗼𝗿𝗿𝗼𝘄 𝗶𝘀 𝗵𝗲𝗿𝗲.

The safety of our people and the future of our society depend not only on infrastructure, but also on strong institutions, innovation, and knowledge. The commissioning of the Centre for DNA Forensics and Criminal Investigation, the first of its kind in Africa, is a major step in that direction. This facility will strengthen criminal investigations, support scientific research, train future experts, and enhance our ability to use modern forensic science to keep our communities safer. It is an investment in justice, security, and the kind of future we are building for generations to come. 𝗧𝗼𝗺𝗼𝗿𝗿𝗼𝘄 𝗶𝘀 𝗵𝗲𝗿𝗲.

Peter Ndubuisi Mbah

15,909 views • 20 days ago

I listened to the first episode of 'The Telepathy Tapes', and I have to admit that I'm impressed. These people can truly tap into our minds, and it seems like the 'scientific consensus' is causing great harm to humanity as a whole! These results are definitely measured using the scientific method, yet they are still rejected! Telepathy is real, and it's part of the human genome. Be sure to read the entire thread and watch the videos! (1/7)🧵

I listened to the first episode of 'The Telepathy Tapes', and I have to admit that I'm impressed. These people can truly tap into our minds, and it seems like the 'scientific consensus' is causing great harm to humanity as a whole! These results are definitely measured using the scientific method, yet they are still rejected! Telepathy is real, and it's part of the human genome. Be sure to read the entire thread and watch the videos! (1/7)🧵

Open Minded Approach

500,192 views • 1 year ago

The frontier labs will crush you. That’s the first thing first friends say when I tell them I’m working on agents for biological research. It’s what I thought too before I started learning about biological agents. Now I’m convinced this space will be dominated by small teams building narrowly scoped, domain-specific models that uniquely embrace the complexity of living systems. So I’m diving in with a team of scientists and engineers who spent years watching models fail in real research settings - and built the “scar tissue” to understand why. We’re building Applied Scientific Intelligence, and some of the early results are encouraging: our models for biological data analysis & literature rank #1 on global benchmarks - outperforming ChatGPT, Claude, Gemini, as well as AI science companies with deep pockets (we’re still bootstrapped ;)). This recently caught the attention of NVIDIA and we partnered with them on our latest model: a new literature agent called “Alexandria” that’s going live in alpha this coming week. DM me if you want to try it out (or sign up in the link below). My main task now is building the distribution engine to get our agents in the hands of biologists. Estimates put the number of researchers at 9-10M globally. I think this number spikes in the next years as science starts to compound like software. Find an exponential curve and get in front of it, they say. Here goes.

The frontier labs will crush you. That’s the first thing first friends say when I tell them I’m working on agents for biological research. It’s what I thought too before I started learning about biological agents. Now I’m convinced this space will be dominated by small teams building narrowly scoped, domain-specific models that uniquely embrace the complexity of living systems. So I’m diving in with a team of scientists and engineers who spent years watching models fail in real research settings - and built the “scar tissue” to understand why. We’re building Applied Scientific Intelligence, and some of the early results are encouraging: our models for biological data analysis & literature rank #1 on global benchmarks - outperforming ChatGPT, Claude, Gemini, as well as AI science companies with deep pockets (we’re still bootstrapped ;)). This recently caught the attention of NVIDIA and we partnered with them on our latest model: a new literature agent called “Alexandria” that’s going live in alpha this coming week. DM me if you want to try it out (or sign up in the link below). My main task now is building the distribution engine to get our agents in the hands of biologists. Estimates put the number of researchers at 9-10M globally. I think this number spikes in the next years as science starts to compound like software. Find an exponential curve and get in front of it, they say. Here goes.

Nate Hindman

13,890 views • 2 months ago

The Genesis Mission calls for new ways to accelerate scientific discovery. This is our contribution Multimodal search across 25M papers is a step toward science discovery that moves at the speed of curiosity. Releasing, - Visually indexed scientific paper dataset with open access 25M papers, 450M+ visually indexed pages. Total 175TB+. All on Deep Lake - Open-source scientific data agent that achieves 48% SOTA on Humanity's Last Exam with tools including the indexed scientific research dataset. Excited to see what discoveries you all uncover with this. Try it and share your most interesting findings.

The Genesis Mission calls for new ways to accelerate scientific discovery. This is our contribution Multimodal search across 25M papers is a step toward science discovery that moves at the speed of curiosity. Releasing, - Visually indexed scientific paper dataset with open access 25M papers, 450M+ visually indexed pages. Total 175TB+. All on Deep Lake - Open-source scientific data agent that achieves 48% SOTA on Humanity's Last Exam with tools including the indexed scientific research dataset. Excited to see what discoveries you all uncover with this. Try it and share your most interesting findings.

Davit

238,086 views • 7 months ago

Update - 10 | 2024/12/29 We built a demo app to ensure easy use of paper submission and workflow customization. What's next? We will up our game to produce analytics and utility tools for the community. Stay tuned for more updates. Join the waitlist and be one of the first who can get hands-on with the app and help us do more human evaluations, pushing the boundaries of how Human and AI can accelerate science together. Link: First milestone is up. Let's recap what we have achieved in the past 10 days: We have established a working Multi-Agents Infrastructure for AI Editors and Peer Reviewers driven by various SOTA LLM models. We have scanned through batches of scientific preprints and manuscripts, producing 200+ AI-generated editorial comments, reviewer personas, paper analyses, error identification, and ratings. All data is well recorded through our metadata tracing workflow. Keep an eye on the upcoming dataset release.

Update - 10 | 2024/12/29 We built a demo app to ensure easy use of paper submission and workflow customization. What's next? We will up our game to produce analytics and utility tools for the community. Stay tuned for more updates. Join the waitlist and be one of the first who can get hands-on with the app and help us do more human evaluations, pushing the boundaries of how Human and AI can accelerate science together. Link: First milestone is up. Let's recap what we have achieved in the past 10 days: We have established a working Multi-Agents Infrastructure for AI Editors and Peer Reviewers driven by various SOTA LLM models. We have scanned through batches of scientific preprints and manuscripts, producing 200+ AI-generated editorial comments, reviewer personas, paper analyses, error identification, and ratings. All data is well recorded through our metadata tracing workflow. Keep an eye on the upcoming dataset release.

ResearchHub Foundation

19,237 views • 1 year ago

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Sam Rodriques

23,301 views • 3 months ago

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Today we’re launching the first and only human-like AI agents in the world. Super Agents™ are the first agents with human‑level skills – they DM you, take @ mentions, send emails, manage docs, tasks, and more. Not just tools or API calls, but real skills fine‑tuned for how teams actually work. The first agents with 100% context – fully native in ClickUp and fully synced from other apps. Super Agents see your work the same way that humans do: tasks, docs, schedules, and conversations all in one place. The first agents that learn from human interactions automatically, without any setup or configuration – when you give feedback, they listen and improve how they work. The first agents with human‑level memory for custom agents – historical memory for every interaction, short-term working memory, and even long‑term memory stored in docs you can literally open, inspect, and edit. The first agents that are literally the same as users – our agentic user model is the same as our user data model. This gives you permissions and capabilities that you and your systems are already familiar with. The first infinite agent catalog – where anyone can create and customize agents in minutes, for literally any type of work imaginable. It's the most intuitive way to build agents on the planet. 95% of companies are failing in AI adoption. The reality is that AI isn't meant to be adopted, it's meant to be adapted – to you. Super Agents are automatically personalized to you and your company using proprietary state-of-the-art agent architecture, orchestration, and tooling. Today is the largest step forward we've ever made towards our mission of making people more productive. Maximize human productivity, with ClickUp Super Agents. Available NOW. For everyone.

Zeb Evans

320,554 views • 6 months ago

🚀 Big milestone: We raised a $235M Series A, co-led by Braidwell and Collective Global! Our team is excited for this next chapter in building the world’s first scientific superintelligence platform to accelerate breakthroughs in life, chemical, and materials sciences. 📣 If the idea of building scientific superintelligence excites you, come build with us. We’re seeking extraordinary, driven people across AI research, software, robotics, biology, chemistry, materials science, and operations. #ScientificSuperintelligence #AI #Innovation

🚀 Big milestone: We raised a $235M Series A, co-led by Braidwell and Collective Global! Our team is excited for this next chapter in building the world’s first scientific superintelligence platform to accelerate breakthroughs in life, chemical, and materials sciences. 📣 If the idea of building scientific superintelligence excites you, come build with us. We’re seeking extraordinary, driven people across AI research, software, robotics, biology, chemistry, materials science, and operations. #ScientificSuperintelligence #AI #Innovation

Lila Sciences

42,934 views • 10 months ago

The FOMO pre-sale is now LIVE! Over the past few months FOMO has been quietly working on the future of memecoins. But there's something we've kept a secret. Memes are just the beginning. Fomo is now the world's first launchpad for AI agents on Solana. We've kept everything you love about FOMO and made it better. Starting tomorrow we have our first Initial Agent Offering (IAO) and the platform opens for all to create their own tokenized AI agents this week. Your agent can learn, interact, do tasks, shill its own token on X, create content on TikTok and YT and so much more. Want to be early to AI Agent token launches? Join the FOMO presale. We are committing 15% of the FOMO supply to our early community members in this presale. Join in and get your FOMO tokens 100% unlocked on TGE. The sale is only for 48 hours and we may sell out sooner!

The FOMO pre-sale is now LIVE! Over the past few months FOMO has been quietly working on the future of memecoins. But there's something we've kept a secret. Memes are just the beginning. Fomo is now the world's first launchpad for AI agents on Solana. We've kept everything you love about FOMO and made it better. Starting tomorrow we have our first Initial Agent Offering (IAO) and the platform opens for all to create their own tokenized AI agents this week. Your agent can learn, interact, do tasks, shill its own token on X, create content on TikTok and YT and so much more. Want to be early to AI Agent token launches? Join the FOMO presale. We are committing 15% of the FOMO supply to our early community members in this presale. Join in and get your FOMO tokens 100% unlocked on TGE. The sale is only for 48 hours and we may sell out sooner!

FOMO

222,883 views • 1 year ago