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.

1.8 million scientific papers are published every year. Keeping up is impossible. Here is a solution: Look at They use AI to summarize and explain things to you. Another amazing use of Large Language Models. AI explaining AI!

Abacus.AI

100,626 subscribers

249,428 views • 3 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Abacus.AI3 years ago

If you enjoy this content, follow @abacusai! There's much more coming!

Kevin Patel3 years ago

I have also recently heard about also, but haven't tried it yet

Pratik Desai3 years ago

I understand what you’re doing, but isn’t the Abstract supposed do that?

Muhammad Iltaf3 years ago

Good

Daniel Yánez Bravo3 years ago

@SaveToNotion #Thread #ai #ChatGPT

Akshay 🚀3 years ago

This is great! Thanks for sharing.

Adrien Bruno3 years ago

Drag and drop? Why you don't use a link?

Ande3 years ago

@remindmetweets in 6 hours

Jose Manuel Castiblanco Quintero3 years ago

...then the author citations would be interesting to review

vrtr3 years ago

@DevHunterYZ What's the error rate?

Related Videos

Conan delicately handling the AI issue at his Harvard commencement speech: “AI is not a problem at Harvard. Here, professors have been able to flag the use of AI using the sophisticated AI software they use to grade papers…despite your fears, AI can not replace you. It is too busy replacing the creeps from Princeton.”

Conan delicately handling the AI issue at his Harvard commencement speech: “AI is not a problem at Harvard. Here, professors have been able to flag the use of AI using the sophisticated AI software they use to grade papers…despite your fears, AI can not replace you. It is too busy replacing the creeps from Princeton.”

Trung Phan

2,856,250 views • 2 months ago

The GOV.UK AI Team is investigating how generative artificial intelligence and large language models could help the millions of people that use GOV.UK every week. Learn more about our #AI Experiments on our blog:

The GOV.UK AI Team is investigating how generative artificial intelligence and large language models could help the millions of people that use GOV.UK every week. Learn more about our #AI Experiments on our blog:

GDS

14,306 views • 2 years ago

The Stoxx 600 European Utilities index is up nearly 26% year to date. The reason is AI. The data centers running large language models use enormous amounts of electricity, and that has put the power companies delivering it in the spotlight

The Stoxx 600 European Utilities index is up nearly 26% year to date. The reason is AI. The data centers running large language models use enormous amounts of electricity, and that has put the power companies delivering it in the spotlight

Reuters

21,428 views • 7 months ago

AI is revolutionizing EVERYTHING. Your competitor is using it to be more productive. Are you? I use AI to refine social media ads—every word optimized. Use it right, and it’s a game-changer.

AI is revolutionizing EVERYTHING. Your competitor is using it to be more productive. Are you? I use AI to refine social media ads—every word optimized. Use it right, and it’s a game-changer.

Kevin O'Leary aka Mr. Wonderful

28,148 views • 1 year ago

Sure, you could use AI to summarize papers and explain them at a level anyone could understand... or you can turn the abstracts into music videos for no reason. The tools are not perfect yet, but the disparate elements (consistent characters, lip syncing, etc.) are evolving fast

Sure, you could use AI to summarize papers and explain them at a level anyone could understand... or you can turn the abstracts into music videos for no reason. The tools are not perfect yet, but the disparate elements (consistent characters, lip syncing, etc.) are evolving fast

Ethan Mollick

95,575 views • 11 months ago

AI data centers are projected to use more energy than the country of Japan. Trump’s solution is beautiful: Force AI companies to build their own power. Meanwhile, Elon applies to launch one *million* satellites to put AI data centers in space.

AI data centers are projected to use more energy than the country of Japan. Trump’s solution is beautiful: Force AI companies to build their own power. Meanwhile, Elon applies to launch one million satellites to put AI data centers in space.

Peter St Onge, Ph.D.

120,212 views • 5 months ago

Dr. Karp on what's behind Palantir's dominance in AI 👇🏻 "we were years ahead for lots of reasons, anticipating what operational AI would mean, meaning AI where you make more money or your revenue goes up and your costs go down. Our platforms are built to use large language models and machine learning in a way in that is actually operationally effective... [we] built this thing called an ontology, which manages large language models in a way where they become crazily useful, both commercially and actually on the battlefield."

Dr. Karp on what's behind Palantir's dominance in AI 👇🏻 "we were years ahead for lots of reasons, anticipating what operational AI would mean, meaning AI where you make more money or your revenue goes up and your costs go down. Our platforms are built to use large language models and machine learning in a way in that is actually operationally effective... [we] built this thing called an ontology, which manages large language models in a way where they become crazily useful, both commercially and actually on the battlefield."

Eliano A. Younes

47,859 views • 1 year ago

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Deep learning. Large language models. Vast capabilities. ☁️💻💡 From chatbots to code generation, learn how #GenerativeAI is redefining #ML-powered capabilities—& how you can build & use large language on #AWS. #MachineLearning #AI 👉

Amazon Web Services

113,313 views • 3 years ago

New tools, models, repos, and papers out of Microsoft Research are here. Use AI and agents? It's worth watching: • MagenticLite from MSR AI Frontiers • Agentic GitHub workflows • Verification‑first agents • Meaning‑matching fine‑tuning • AI transition + the economy

New tools, models, repos, and papers out of Microsoft Research are here. Use AI and agents? It's worth watching: • MagenticLite from MSR AI Frontiers • Agentic GitHub workflows • Verification‑first agents • Meaning‑matching fine‑tuning • AI transition + the economy

Microsoft Research

3,447,138 views • 2 months ago

Researchers are using ChatGPT to generate content for their papers...and are getting caught. Want to avoid this kind of embarrassement? Use Consensus, it has an AI-powered Copilot integrated with academic databses. Ask it to generate an outline for a literature review. It will give you an outline with citations to published research. No nonsense like "As an AI language model..."

Researchers are using ChatGPT to generate content for their papers...and are getting caught. Want to avoid this kind of embarrassement? Use Consensus, it has an AI-powered Copilot integrated with academic databses. Ask it to generate an outline for a literature review. It will give you an outline with citations to published research. No nonsense like "As an AI language model..."

Mushtaq Bilal, PhD

122,389 views • 2 years ago

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

New Anthropic research: Tracing the thoughts of a large language model. We built a "microscope" to inspect what happens inside AI models and use it to understand Claude’s (often complex and surprising) internal mechanisms.

Anthropic

1,572,663 views • 1 year ago

Every month thousands of research papers are published with AI-generated citations to fake papers. So, we've built a Hallucination Checker. Just paste a bibliography and it'll which paper is real and which fake. Check it out at We're offering lifetime deals.

Every month thousands of research papers are published with AI-generated citations to fake papers. So, we've built a Hallucination Checker. Just paste a bibliography and it'll which paper is real and which fake. Check it out at We're offering lifetime deals.

Mushtaq Bilal, PhD

22,391 views • 2 months ago

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

Introducing Memory 101 🧠 Every ai tool you use is a goldfish. brilliant for one chat, close the tab and it forgets you completely. memory is the most underbuilt layer in ai right now. so we're explaining how it actually works, one episode at a time. coming up: → rag vs memory, why most "ai memory" is just search → the 5 things real memory needs: facts, profiles, graphs, time, forgetting → why good memory has to forget things follow along!

supermemory

17,235 views • 1 month ago

OpenGradient Chat is the easiest way to use frontier AI models without giving up your privacy.

OpenGradient Chat is the easiest way to use frontier AI models without giving up your privacy.

OpenGradient (∇, ∇)

36,280 views • 1 month ago

‘THE SIMPSONS’ deals with the use of AI in the show’s latest episode. “Dad can you please explain to Bart why using AI to do his homework is wrong?”

‘THE SIMPSONS’ deals with the use of AI in the show’s latest episode. “Dad can you please explain to Bart why using AI to do his homework is wrong?”

DiscussingFilm

2,281,659 views • 9 months ago

Unaligned #2: into "always listening" AI startup: Rewind's founder Dan Siroker. Large Language Models have made a new kind of software possible: one that always listens to you, keeping notes, remembering things, and much more. Scary? Yes, even to me. How about you?

Unaligned #2: into "always listening" AI startup: Rewind's founder Dan Siroker. Large Language Models have made a new kind of software possible: one that always listens to you, keeping notes, remembering things, and much more. Scary? Yes, even to me. How about you?

Robert Scoble

103,688 views • 2 years ago

AI fully taking over 3D is inevitable you can now add 3D bg for 3D models inside 3d software using World Labs's Marble and.. view in real time and even use Octane's 3DGS to light up the model without adding lights this is impossible w/o AI

AI fully taking over 3D is inevitable you can now add 3D bg for 3D models inside 3d software using World Labs's Marble and.. view in real time and even use Octane's 3DGS to light up the model without adding lights this is impossible w/o AI

el.cine

174,533 views • 8 months ago

99% of AI applications are cool-looking demos. Impressive, but don't get fooled by the hype. It takes a lot to build enterprise-grade products that deliver real value. I have at least three weekly conversations with companies that want to use a Large Language Model with their data. The demand is huge! Here is one idea about what you can do to help. The use cases that most of these companies want to solve are similar: They have an extensive knowledge base and want to build a simple application that uses that information to answer questions. In other words, they need help building Retrieval Augmented Generation (RAG) applications they can use in many different scenarios: 1. To train new employees 2. To help their support team 3. To search old meetings and documents 4. To help with their research However, building these systems is not straightforward. Yes, there's a lot of information online, but there aren't enough people who know how to create solutions that work. Here is the idea: Today, you can build an enterprise-grade RAG application without writing code. A couple of MIT PhDs with 10+ years of experience building AI applications created . It's a no-code platform for building applications using Large Language Models. They are partnering with me on this post. You can use Stack AI to create, test, and deploy an end-to-end production-ready AI system. It's SOC-2, HIPAA, and GDPR compliant and offers SSO, role management, access control, and on-premise deployments. Of course, you can use the platform with any LLM on the market now. It's the whole nine yards for building AI applications. Check them out here: 2023 was about models. 2024 is about the tools using these models to build production-ready applications. That's where I'd start.

99% of AI applications are cool-looking demos. Impressive, but don't get fooled by the hype. It takes a lot to build enterprise-grade products that deliver real value. I have at least three weekly conversations with companies that want to use a Large Language Model with their data. The demand is huge! Here is one idea about what you can do to help. The use cases that most of these companies want to solve are similar: They have an extensive knowledge base and want to build a simple application that uses that information to answer questions. In other words, they need help building Retrieval Augmented Generation (RAG) applications they can use in many different scenarios: 1. To train new employees 2. To help their support team 3. To search old meetings and documents 4. To help with their research However, building these systems is not straightforward. Yes, there's a lot of information online, but there aren't enough people who know how to create solutions that work. Here is the idea: Today, you can build an enterprise-grade RAG application without writing code. A couple of MIT PhDs with 10+ years of experience building AI applications created . It's a no-code platform for building applications using Large Language Models. They are partnering with me on this post. You can use Stack AI to create, test, and deploy an end-to-end production-ready AI system. It's SOC-2, HIPAA, and GDPR compliant and offers SSO, role management, access control, and on-premise deployments. Of course, you can use the platform with any LLM on the market now. It's the whole nine yards for building AI applications. Check them out here: 2023 was about models. 2024 is about the tools using these models to build production-ready applications. That's where I'd start.

Santiago

197,675 views • 2 years ago

The lack of understanding of how current AI/ large language models work makes us susceptible to thinking that AI is more powerful and all-knowing than it actually is. That’s what concerns me the most.

The lack of understanding of how current AI/ large language models work makes us susceptible to thinking that AI is more powerful and all-knowing than it actually is. That’s what concerns me the most.

Sinead Bovell

143,642 views • 3 years ago

Over half of U.S. law firm attorneys now use generative AI, up from under a third last year. Large firms lead in AI investment and training. Despite reliability concerns, AI is easing workloads. Dive deep into data with the 2025 Law360 Pulse AI Survey, coming Tuesday.

Over half of U.S. law firm attorneys now use generative AI, up from under a third last year. Large firms lead in AI investment and training. Despite reliability concerns, AI is easing workloads. Dive deep into data with the 2025 Law360 Pulse AI Survey, coming Tuesday.

Law360

13,214 views • 1 year ago