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.

25 algorithms every programmer should know: Let's start with my top favorite 10. If nothing else, you should read about these algorithms and have a good idea of how they work: 1. Linear search to find an element in a list 2. Binary search to find an element on... a sorted list 3. Bubble sort to sort a list 4. Merge sort will also sort lists 5. Quicksort to sort the list and do it fast 6. Dijkstra to find the shortest path in a graph 7. Breadth-first Search (BFS) for trees or graphs 8. Depth-first search (DFS) for trees or graphs 9. Huffman for doing data compression 10. Anything related to dynamic programming Learning about algorithms is like getting tattoos: you never have enough. Here are another 5 algorithms that will help you go beyond the basics: 11. Kruskal for the finding minimum spanning tree 12. Floyd Warshall, shortest paths in a graph 13. Union Find to detect cycles in a graph 14. Bellman-Ford, shortest path in a graph 15. Lee for finding the shortest path in a maze If you are serious about this topic, I recommend learning about algorithms' space and time complexity. People usually refer to this topic as "Big O" notation. You should build a good intuition about the performance of different algorithms and learn how to evaluate them. Machine Learning will rule the next 50 years, so the next 10 algorithms you can't ignore are the following: 16. Linear Regression 17. Logistic Regression 18. Decision Trees 19. Bayes' theorem 20. k-Nearest Neighbors (kNN) 21. Every algorithm related to neural networks 22. K-means 23. Random forest 24. Gradient boosting algorithms 25. Any dimensionality reduction algorithm (PCA, for instance) There are many more mind-blowing algorithms! I haven't found a better way to understand how computers work from a first-principles point of view than reading about different algorithms. Take a look at the attached video.show more

Santiago

454,815 subscribers

274,092 views • 2 years ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

9 Comments

John Crickett2 years ago

99% of programmers will never write one of this professionally. Ironically the ones I have done aren't on this list.

Santiago2 years ago

They won't. But the usefulness of learning these algorithms is not to write them later. That's the argument I make in the video.

Raul Junco2 years ago

The main benefit of understanding algorithms is the skills you learn to solve problems efficiently and effectively.

Byron Goodman2 years ago

I've never implemented DFS except in college, and graduate school. I have implemented A* and variations (BFS) many, many times. The problem with DFS is incomplete graphs and the bias introduced. A* requires more memory in comparison, but memory is cheap. Dijkstra's algorithm is basically A* so you can take that one off as well.

Calc Consulting2 years ago

21 Every algorithm related to neural networks 😂

Santiago2 years ago

Yup :)

Edward Manda2 years ago

What’s the name of the book 📖?

Anirudh Sharma2 years ago

Learning algorithms is not only useful for interviews but also beneficial for becoming a better problem solver.

inner voice priv/acc2 years ago

Seriously! 📺 vids!

Related Videos

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Experiments in progress. The one on the right has been learning for ~3 hours, the one in the middle for ~1 hour, and the one on the left just started a few minutes ago. The initial motivation for making the physical Atari was just to commit ourselves to a subset of algorithms that can make progress in this setup. This commitment rules out algorithms that require billions of samples to learn (or worse, require multiple environments running in parallel). Atari games are simple enough that we should be able to show learning on them in a short amount of time with no prior knowledge. Since then, I've realized that this setup is also a good way to compare different paradigms in robotics in a principled way. These paradigms are sim2real, learning from tele-operated data, and learning directly on the robots. So far, I have observed that getting sim2real to work reliably is hard. It requires tweaks that don't scale. Policies that can play perfectly in simulation fall apart because of latencies and the messiness of the real world. These aspects could be modeled to improve the simulation, but not without sinking significant human engineering hours. I have higher hopes for learning from tele-operated data, but that requires a human to learn the task first. These experiments are on my to-do list. I have to learn to play some of the games well through the robot. I’m half-decent at playing Pong and Ms Pacman now. Learning directly on robots is looking like the most promising approach. This approach takes away pesky distribution shifts and makes it possible to have algorithms that continually improve with more data and time without any human intervention. It feels great to let experiments run overnight and wake up to find improved policies. With learning on robots, I should, in principle, be able to go on a long vacation and come back to find better policies for complex tasks beyond Atari games. Whether that is possible with current learning algorithms is a different question.

Khurram Javed

52,110 views • 9 months ago

If you could only learn one thing that will be relevant for the next 10-20 years, focus on learning how to deal with data. The future is not about faster hardware, smarter algorithms, or better ideas. The future is about DATA, and those who know how to deal with it will stay relevant much longer than anyone else. I recorded a video to show you how easy it is to get started. In the video, I'm using Kestra. For a long time, I was a fan of AirFlow. Then, I moved to AWS Step Functions. Today, I only use Kestra. Kestra is open-source (repo link below) and kind enough to sponsor my work. The video will show you how easy it is to do the following: 1. Run Kestra locally (literally, one command) 2. Build a simple flow 3. Run Python scripts as part of your flow 4. Connect to HuggingFace models If you have never built a data pipeline, open Kestra's Quick Start Guide and follow their examples. (I think it will take you one weekend to feel comfortable with the application and build the courage you need to get into more serious work.)

If you could only learn one thing that will be relevant for the next 10-20 years, focus on learning how to deal with data. The future is not about faster hardware, smarter algorithms, or better ideas. The future is about DATA, and those who know how to deal with it will stay relevant much longer than anyone else. I recorded a video to show you how easy it is to get started. In the video, I'm using Kestra. For a long time, I was a fan of AirFlow. Then, I moved to AWS Step Functions. Today, I only use Kestra. Kestra is open-source (repo link below) and kind enough to sponsor my work. The video will show you how easy it is to do the following: 1. Run Kestra locally (literally, one command) 2. Build a simple flow 3. Run Python scripts as part of your flow 4. Connect to HuggingFace models If you have never built a data pipeline, open Kestra's Quick Start Guide and follow their examples. (I think it will take you one weekend to feel comfortable with the application and build the courage you need to get into more serious work.)

Santiago

51,100 views • 1 year ago

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

a playlist of 30 youtube videos to learn machine learning fundamentals from scratch if you're struggling on where to start learning ML, this list goes this "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

117,748 views • 1 year ago

Delta Airlines to begin using artificial intelligence algorithms to scrape your emails and more to determine the maximum amount you’re willing to spend on tickets, then adjust your price Example: If you have a death in the family, they’ll know it’s urgent and the price will go up ‘Delta says it's "fully reengineering how we price" airfare - leaning into Al algorithms that set the maximum price you're willing to spend, based on surveillance technology. About 3% of Delta's domestic ticket prices are now determined by artificial intelligence - and Delta plans to raise that to 20% by the end of the year.’ - More Perfect Union “Delta Airlines just announced on their earnings call that they're going to start using some of these algorithms to price some of their tickets. And imagine a world in which you have a death in the family, you have to go home for a funeral. And they know that through scraping your email, that is, you know, announcing when the service is going to be. They know you're in a tight spot, and so you're going to be charged much more because of that. There's so much data collected about individual people by data brokers, by this whole shadowy ecosystem that's just tracking you through your phone, through your browsing history. — There is a serious worry that companies will be able to do this.” Imagine how many other businesses are going to start doing the same thing

Delta Airlines to begin using artificial intelligence algorithms to scrape your emails and more to determine the maximum amount you’re willing to spend on tickets, then adjust your price Example: If you have a death in the family, they’ll know it’s urgent and the price will go up ‘Delta says it's "fully reengineering how we price" airfare - leaning into Al algorithms that set the maximum price you're willing to spend, based on surveillance technology. About 3% of Delta's domestic ticket prices are now determined by artificial intelligence - and Delta plans to raise that to 20% by the end of the year.’ - More Perfect Union “Delta Airlines just announced on their earnings call that they're going to start using some of these algorithms to price some of their tickets. And imagine a world in which you have a death in the family, you have to go home for a funeral. And they know that through scraping your email, that is, you know, announcing when the service is going to be. They know you're in a tight spot, and so you're going to be charged much more because of that. There's so much data collected about individual people by data brokers, by this whole shadowy ecosystem that's just tracking you through your phone, through your browsing history. — There is a serious worry that companies will be able to do this.” Imagine how many other businesses are going to start doing the same thing

Wall Street Apes

1,335,409 views • 1 year ago

.Dwarkesh Patel's episode with Eric Jang is awesome. Eric has a rare gift for making complicated ideas feel simple, which is exactly what struck me when I first met him at a dinner and immediately peppered him with questions. If you are looking to hear more from him, listen to our conversation from a couple years ago! "The history of neural networks and actually many things in AI have been inspired a lot by biology, like genetic algorithms, evolutionary algorithms, processes in both neuroscience and psychology and biology and so forth. I think drawing from nature is a great way to get inspiration... And this is going to get me a lot of flack from the scientific community, but I feel like in the last decade and a half-ish of deep learning progress, the vast majority of major contributions have come from people who did not really adhere to that way of thinking, but more like, how do I push as much data as fast as possible onto my GPU? It just empirically seems to me that people who are very attached to the idea of replicating a particular nature inspired architecture at the expense of enabling brute force compute... do not make the best algorithms. There's this essay by Sara Hooker called the the hardware lottery where it's arguing that people who focused on maximizing and designing their algorithms to suit the hardware so that it could run the brute force thing as fast as possible tended to win. "

.Dwarkesh Patel's episode with Eric Jang is awesome. Eric has a rare gift for making complicated ideas feel simple, which is exactly what struck me when I first met him at a dinner and immediately peppered him with questions. If you are looking to hear more from him, listen to our conversation from a couple years ago! "The history of neural networks and actually many things in AI have been inspired a lot by biology, like genetic algorithms, evolutionary algorithms, processes in both neuroscience and psychology and biology and so forth. I think drawing from nature is a great way to get inspiration... And this is going to get me a lot of flack from the scientific community, but I feel like in the last decade and a half-ish of deep learning progress, the vast majority of major contributions have come from people who did not really adhere to that way of thinking, but more like, how do I push as much data as fast as possible onto my GPU? It just empirically seems to me that people who are very attached to the idea of replicating a particular nature inspired architecture at the expense of enabling brute force compute... do not make the best algorithms. There's this essay by Sara Hooker called the the hardware lottery where it's arguing that people who focused on maximizing and designing their algorithms to suit the hardware so that it could run the brute force thing as fast as possible tended to win. "

Sabrina Halper

39,759 views • 4 months ago

$Extropic founder Beff (e/acc) on why running probabilistic AI on deterministic hardware is quietly the biggest local optimum in computing "You have Landauer's principle. Essentially you have a minimum cost of erasing a bit." "Every time you reset a bit in a classical computer, your bit is actually random. You don't know what state it is, and then you have to reset it to a deterministic state. So you have a Maxwell's demon for every bit, for every clock cycle. I'm tired of paying the demon tax." "If you go with fractional bits, you don't need to do full bit operations. Running hardware probabilistically is just much more power efficient." "All the algorithms we want to run these days, whether it's PageRank, whether it's recommender systems, whether it's diffusion models, whether it's transformers, they're all probabilistic algorithms." "Why are we paying the Maxwell's demon tax to run probabilistic algorithms on deterministic hardware? It just makes zero sense, and we've just been caught in a local optima." "It takes a true set of autists that are like, screw the whole stack, we're going to start from scratch. This has the bones to eat the world." Extropic$

Extropic founder Beff (e/acc) on why running probabilistic AI on deterministic hardware is quietly the biggest local optimum in computing "You have Landauer's principle. Essentially you have a minimum cost of erasing a bit." "Every time you reset a bit in a classical computer, your bit is actually random. You don't know what state it is, and then you have to reset it to a deterministic state. So you have a Maxwell's demon for every bit, for every clock cycle. I'm tired of paying the demon tax." "If you go with fractional bits, you don't need to do full bit operations. Running hardware probabilistically is just much more power efficient." "All the algorithms we want to run these days, whether it's PageRank, whether it's recommender systems, whether it's diffusion models, whether it's transformers, they're all probabilistic algorithms." "Why are we paying the Maxwell's demon tax to run probabilistic algorithms on deterministic hardware? It just makes zero sense, and we've just been caught in a local optima." "It takes a true set of autists that are like, screw the whole stack, we're going to start from scratch. This has the bones to eat the world." Extropic

MTS

33,856 views • 1 month ago

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

if you're struggling on where to start learning ML, here’s a playlist of 30 youtube videos to learn machine learning fundamentals from scratch "Machine Learning: Teach by Doing" is a solid choice to learn both theory and code. (1) Introduction to Machine Learning Teach by Doing: (2) What is Machine Learning? History of Machine Learning: (3) Types of ML Models: (4) 6 steps of any ML project: (5) Install Python and VSCode and run your first code: (6) Linear Classifiers Part 1: (7) Linear Classifiers Part 2: (8) Jupyter Notebook, Numpy and Scikit-Learn: (9) Running the Random Linear Classifier Algorithm in Python: (10) The oldest ML model - Perceptron: (11) Coding the Perceptron: (12) Perceptron Convergence Theorem: (13) Magic of features in Machine Learning: (14) One hot encoding: (15) Logistic Regression Part 1: (16) Cross Entropy Loss: (17) How gradient descent works: (18) Logistic Regression from scratch in Python: (19) Introduction to Regularization: (20) Implementing Regularization in Python: (21) Linear Regression Introduction: (22) Ordinary Least Squares step by step implementation: (23) Ridge regression fundamentals and intuition: (24) Regression recap for interviews: (25) Neural network architecture in 30 minutes: (26) Backpropagation intuition: (27) Neural network activation functions: (28) Momentum in gradient descent: (29) Hands on neural network training in Python: (30) Introduction to Convolutional Neural Networks (CNNs):

ℏεsam

109,550 views • 1 year ago

We just discovered faster sorting algorithms! Here is a 60-second explanation of what happened: DeepMind turned the sorting problem into a puzzle, where the goal of an agent is to organize a list of instructions to find a correct and efficient algorithm. Think Tetris, but using lines of code. They used Deep Reinforcement Learning to train the agent who only wins the game if it finds an efficient algorithm. They called it "AlphaDev," and it didn't disappoint: AlphaDev found shorter and faster solutions for several sorting variants that we use trillions of times daily! This is a big deal. Conceptually, sorting is still an O(N log N) problem; Deepmind didn't change that. But practically speaking, and thanks to AlphaDev, we have code that runs faster. You should read their paper. They compared the current version of these algorithms and the new version they discovered. In some cases, they made significant improvements. Some people aren't happy with the way DeepMind is promoting this work. They argue the results aren't as breathtaking as the headlines claim. We can discuss their marketing, but this is undoubtedly a significant step with a real impact and the potential to generalize to more areas. The new algorithms that AlphaDev found seem trivial, yet no human found them before. That's the true power of Artificial Intelligence.

We just discovered faster sorting algorithms! Here is a 60-second explanation of what happened: DeepMind turned the sorting problem into a puzzle, where the goal of an agent is to organize a list of instructions to find a correct and efficient algorithm. Think Tetris, but using lines of code. They used Deep Reinforcement Learning to train the agent who only wins the game if it finds an efficient algorithm. They called it "AlphaDev," and it didn't disappoint: AlphaDev found shorter and faster solutions for several sorting variants that we use trillions of times daily! This is a big deal. Conceptually, sorting is still an O(N log N) problem; Deepmind didn't change that. But practically speaking, and thanks to AlphaDev, we have code that runs faster. You should read their paper. They compared the current version of these algorithms and the new version they discovered. In some cases, they made significant improvements. Some people aren't happy with the way DeepMind is promoting this work. They argue the results aren't as breathtaking as the headlines claim. We can discuss their marketing, but this is undoubtedly a significant step with a real impact and the potential to generalize to more areas. The new algorithms that AlphaDev found seem trivial, yet no human found them before. That's the true power of Artificial Intelligence.

Santiago

407,826 views • 3 years ago

I had a fantastic time discussing with the learning legend Justin Skycak from Math Academy about learning math in the modern age. we've talked about his quite impressive self-learning journey (3000h of math in high school) all the way to how he hand curated the initial knowledge graph for math academy to make that process more efficient. great lively 3h discussion here are the chapters: 0:00:00 - intro: 0:02:10 - justin background 0:05:45 - 3000h math self study in high school 0:11:45 - what a day looked like for that 3000h stretch 0:16:10 - meta-learning vs pure math learning 0:21:50 - when did you get into cognitive neuro? 0:29:55 - how did the fundamental math helped in your research projects 0:43:10 - what does the math academy learning system looks like 0:47:34 - how did you guys build the 2000 topic knowledge graph 1:01:15 - would LLM be useful as an interface to that knowledge graph for the students? 1:10:46 - how does the FIRe spaced repetition algorithm works? 1:17:34 - does the same knowledge graph structure would work for physics? or other topic?: 1:34:05 - how do you understand the subject vs the curiculum 1:35:50 - is there a connection between studying math and learning a sport? 1:42:00 - do you think in math doing and teaching requires different skills? 1:56:25 - could you get understanding without automaticy? 2:05:35 - do you see any upside of confusion in learning? 2:14:11 - learning math as an adult? 2:19:20 - how to fill the motivation gap after learning the fundamental? 2:24:10 - how should teaching math for kids and adults balance fundamentals and creativity? 2:33:55 - is it ever too late to learn math seriously? 2:46:00 - mastery learning vs ultra learning 2:51:30 - top-down vs bottom-up 2:53:40 - mastery learning for domain without a structured hierarchical structure? 2:56:30 - neurodivergence / adhd for structured math learning? 3:06:20 - amateur mathematician augmented with technology will be able to contribute to research? 3:14:37 - what are you most excited about right now in term of learning enjoy!

I had a fantastic time discussing with the learning legend Justin Skycak from Math Academy about learning math in the modern age. we've talked about his quite impressive self-learning journey (3000h of math in high school) all the way to how he hand curated the initial knowledge graph for math academy to make that process more efficient. great lively 3h discussion here are the chapters: 0:00:00 - intro: 0:02:10 - justin background 0:05:45 - 3000h math self study in high school 0:11:45 - what a day looked like for that 3000h stretch 0:16:10 - meta-learning vs pure math learning 0:21:50 - when did you get into cognitive neuro? 0:29:55 - how did the fundamental math helped in your research projects 0:43:10 - what does the math academy learning system looks like 0:47:34 - how did you guys build the 2000 topic knowledge graph 1:01:15 - would LLM be useful as an interface to that knowledge graph for the students? 1:10:46 - how does the FIRe spaced repetition algorithm works? 1:17:34 - does the same knowledge graph structure would work for physics? or other topic?: 1:34:05 - how do you understand the subject vs the curiculum 1:35:50 - is there a connection between studying math and learning a sport? 1:42:00 - do you think in math doing and teaching requires different skills? 1:56:25 - could you get understanding without automaticy? 2:05:35 - do you see any upside of confusion in learning? 2:14:11 - learning math as an adult? 2:19:20 - how to fill the motivation gap after learning the fundamental? 2:24:10 - how should teaching math for kids and adults balance fundamentals and creativity? 2:33:55 - is it ever too late to learn math seriously? 2:46:00 - mastery learning vs ultra learning 2:51:30 - top-down vs bottom-up 2:53:40 - mastery learning for domain without a structured hierarchical structure? 2:56:30 - neurodivergence / adhd for structured math learning? 3:06:20 - amateur mathematician augmented with technology will be able to contribute to research? 3:14:37 - what are you most excited about right now in term of learning enjoy!

Yacine Mahdid

57,320 views • 5 months ago

We asked Zachary Perret to break down how complicated fraud detection is. "The hard part is twofold. First, you have to put in all of your historical data to find anomalous patterns." "In Plaid's case, the question is: can we take the data we see across all of the fintech apps and users and find consistently occurring patterns?" "For example, if you signed up for 6 lending products today, it's obviously a potentially fraudulent loan that you're trying to take out." "Fraud changes every day. Problem No.2 is can you change the analysis you are doing at the speed (that fraud evolves)? Are the algorithms chasing the fraudsters in the way they need to? It's a constantly evolving game."

We asked Zachary Perret to break down how complicated fraud detection is. "The hard part is twofold. First, you have to put in all of your historical data to find anomalous patterns." "In Plaid's case, the question is: can we take the data we see across all of the fintech apps and users and find consistently occurring patterns?" "For example, if you signed up for 6 lending products today, it's obviously a potentially fraudulent loan that you're trying to take out." "Fraud changes every day. Problem No.2 is can you change the analysis you are doing at the speed (that fraud evolves)? Are the algorithms chasing the fraudsters in the way they need to? It's a constantly evolving game."

TBPN

19,702 views • 1 year ago

Not a fan of Knowledge Graphs, but recently I started using them more often for a surprising reason: to build non-trivial private verifiers for agentic search. For those who don't know, building a private eval set for a scaffolded LLM in 2026 is really challenging, like seriously hard. It takes a lot of effort to find a question that's non-trivial to a scaffolded LLM yet still answerable. To find those question-answer pairs, I built a knowledge graph extractor where you can throw a corpus at it, and it extracts the entity relations using qwen3.6-35b-a3b-MTP on an L4 at 70 tps (which is really good for such a low-budget GPU). Then I mark out the longest path in the graph and use it to generate challenging question-answer pairs. The idea is to find those genuinely multi-hop fact chains that are verifiable from the corpus, to stress-test the agentic search system.

Not a fan of Knowledge Graphs, but recently I started using them more often for a surprising reason: to build non-trivial private verifiers for agentic search. For those who don't know, building a private eval set for a scaffolded LLM in 2026 is really challenging, like seriously hard. It takes a lot of effort to find a question that's non-trivial to a scaffolded LLM yet still answerable. To find those question-answer pairs, I built a knowledge graph extractor where you can throw a corpus at it, and it extracts the entity relations using qwen3.6-35b-a3b-MTP on an L4 at 70 tps (which is really good for such a low-budget GPU). Then I mark out the longest path in the graph and use it to generate challenging question-answer pairs. The idea is to find those genuinely multi-hop fact chains that are verifiable from the corpus, to stress-test the agentic search system.

Han Xiao

58,118 views • 3 months ago

I understand that it is physically painful to like such videos, but this is the only way to raise posts in X-algorithms, people need to see the truth about what the Russians are doing on the territory of Ukraine. After a Russian drone spotted volunteers delivering humanitarian aid to civilians in the Ukrainian town of Chasiv Yar, they all started to be shelled, and this trend is constant, according to local residents. Thank you volunteers for the video so we can have a chance to show it to the world! Tik Tok _vitaminishe_

I understand that it is physically painful to like such videos, but this is the only way to raise posts in X-algorithms, people need to see the truth about what the Russians are doing on the territory of Ukraine. After a Russian drone spotted volunteers delivering humanitarian aid to civilians in the Ukrainian town of Chasiv Yar, they all started to be shelled, and this trend is constant, according to local residents. Thank you volunteers for the video so we can have a chance to show it to the world! Tik Tok _vitaminishe_

Katerina Horbunova

161,925 views • 2 years ago

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

126,559 views • 11 months ago

Jerry Tworek on what was required to get RL to work for o1. Sounds a lot like the modern GRPO recipe: "Everyone already today roughly knows the formula from a high level, which is, you know, the idea that you need a reward from the environment is not particularly new. Rewards in RL have been around for a long time. But a lot of the difficulties are, like, one thing, this simple idea of doing multiple rollouts for a single prompt to build a baseline, is a really, really powerful one, and that helps a lot. There’s a lot about numerical stability. There are some things that had to be removed from PPO to make the algorithm work better and scale better. There’s always this notion that simplicity is what makes scaling work. Your algorithm needs to be simple. So, like, you know, today’s set of algorithms for scaling are actually that simple in multiple ways. But this is what I was able to get to scale."

Jerry Tworek on what was required to get RL to work for o1. Sounds a lot like the modern GRPO recipe: "Everyone already today roughly knows the formula from a high level, which is, you know, the idea that you need a reward from the environment is not particularly new. Rewards in RL have been around for a long time. But a lot of the difficulties are, like, one thing, this simple idea of doing multiple rollouts for a single prompt to build a baseline, is a really, really powerful one, and that helps a lot. There’s a lot about numerical stability. There are some things that had to be removed from PPO to make the algorithm work better and scale better. There’s always this notion that simplicity is what makes scaling work. Your algorithm needs to be simple. So, like, you know, today’s set of algorithms for scaling are actually that simple in multiple ways. But this is what I was able to get to scale."

Adam Karvonen

22,884 views • 12 days ago

BOOM: CNN panel EXPLODES when Scott Jennings argues Americans *should* be proud to live in the greatest country on Earth and that it’s the left who hates this country, hate its history, and fear for the future.... “I like it when our leaders talk about a hopeful future. I think that's good for the country. I — I guess I sort of reject the premise of the conversation a little in that, you know, these are somehow dark times and we're living through this uncertain rough patch. I mean, I'm pretty happy, you know, and I think a lot of people are.” “If you looked at the splits [in an NBC News poll] on how people feel about America, the promise of America, if you look at whether they’re proud of their country or not — ,,Gallup has measured this — Republicans and conservatives are proud to be Americans, and it’s Democrats and liberals who are not. And I think if you looked at the splits in that, you’d find — you — you’d find — you’d find — you’d find the two lines on the graph going this way. And honestly, I mean, I think there’s a political movement in this country right now built on telling people that America is rotten at its core. It’s not the Republican ideology.” “The problem is telling you the truth about the numbers?” “I’m not going to give you a break about the math!” “Yeah. I agree. We have we have Democrats cheering for Iran. I totally agree with you. It’s crazy.” “What you’re raising, though, is the issue of — we’re not living in a shared reality. This is the biggest difference today for the rest of the country’s history. And it's hard to have a shared national purpose when you don’t have a shared reality. And so, I think one of the things we're going to have to grapple with as Americans is, you know, how do we have more of a shared reality when it comes to our political [differences]”

BOOM: CNN panel EXPLODES when Scott Jennings argues Americans should be proud to live in the greatest country on Earth and that it’s the left who hates this country, hate its history, and fear for the future.... “I like it when our leaders talk about a hopeful future. I think that's good for the country. I — I guess I sort of reject the premise of the conversation a little in that, you know, these are somehow dark times and we're living through this uncertain rough patch. I mean, I'm pretty happy, you know, and I think a lot of people are.” “If you looked at the splits [in an NBC News poll] on how people feel about America, the promise of America, if you look at whether they’re proud of their country or not — ,,Gallup has measured this — Republicans and conservatives are proud to be Americans, and it’s Democrats and liberals who are not. And I think if you looked at the splits in that, you’d find — you — you’d find — you’d find — you’d find the two lines on the graph going this way. And honestly, I mean, I think there’s a political movement in this country right now built on telling people that America is rotten at its core. It’s not the Republican ideology.” “The problem is telling you the truth about the numbers?” “I’m not going to give you a break about the math!” “Yeah. I agree. We have we have Democrats cheering for Iran. I totally agree with you. It’s crazy.” “What you’re raising, though, is the issue of — we’re not living in a shared reality. This is the biggest difference today for the rest of the country’s history. And it's hard to have a shared national purpose when you don’t have a shared reality. And so, I think one of the things we're going to have to grapple with as Americans is, you know, how do we have more of a shared reality when it comes to our political [differences]”

Curtis Houck

110,997 views • 5 months ago

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

How to extract data from papers for literature review in seconds? 1. Go to 2. Upload 2-3 papers you already know are relevant 3. Start with clicking on one paper 4. ResearchCollab do the following for the paper ✦ Provide a short overview of the paper ✦ Identify weaknesses in the paper ✦ Share papers that contrast the existing paper ✦ Extract meta data about the paper ✦ Evaluate each part (e.g., methodology) of the paper ✦ Provide AI chat to extract any other data 5. Now click on the Related Papers button at top right 6. You will get papers related to the seed paper 7. You can click on each paper and read its abstract 8. If you find it relevant, just add it to your list of papers 9. Do the same for the other 2 seed papers 10. This way you will collect all relevant papers 11. And extract data from those papers After this, analyse the data and report the findings. Try ResearchCollab today:

Faheem Ullah

26,494 views • 7 months ago

STANFORD JUST PUT ITS ENTIRE ARTIFICIAL INTELLIGENCE CURRICULUM ON YOUTUBE FOR FREE. CS221. The same course that produced engineers now running AI labs, building frontier models, and getting paid $500,000 a year at the companies everyone is trying to work for. Most people have never heard of it. The ones who have are not telling you about it. Here is what the course actually covers: Search algorithms. The mathematical foundation behind every AI that finds optimal solutions in complex environments. Constraint satisfaction. How AI reasons through problems with thousands of interdependent variables simultaneously. Markov decision processes. The probabilistic framework behind every AI agent that makes sequential decisions under uncertainty. Machine learning from first principles. Not how to use sklearn. How the math actually works underneath it. Neural networks. Built from the ground up before jumping to applications. Logic and knowledge representation. How AI systems reason about the world formally. Natural language processing. The foundation of everything happening in LLMs right now. Robotics and computer vision. How AI perceives and acts in physical environments. Every concept that powers every AI product you use daily is in this curriculum. Not a surface level overview. The actual mathematics. The actual algorithms. The actual reasoning. This is what separates engineers who build AI from operators who use it. Stanford charged $60,000 a year for students to sit in this classroom. They put the whole thing on YouTube. Bookmark this before you open any other AI resource today.

STANFORD JUST PUT ITS ENTIRE ARTIFICIAL INTELLIGENCE CURRICULUM ON YOUTUBE FOR FREE. CS221. The same course that produced engineers now running AI labs, building frontier models, and getting paid $500,000 a year at the companies everyone is trying to work for. Most people have never heard of it. The ones who have are not telling you about it. Here is what the course actually covers: Search algorithms. The mathematical foundation behind every AI that finds optimal solutions in complex environments. Constraint satisfaction. How AI reasons through problems with thousands of interdependent variables simultaneously. Markov decision processes. The probabilistic framework behind every AI agent that makes sequential decisions under uncertainty. Machine learning from first principles. Not how to use sklearn. How the math actually works underneath it. Neural networks. Built from the ground up before jumping to applications. Logic and knowledge representation. How AI systems reason about the world formally. Natural language processing. The foundation of everything happening in LLMs right now. Robotics and computer vision. How AI perceives and acts in physical environments. Every concept that powers every AI product you use daily is in this curriculum. Not a surface level overview. The actual mathematics. The actual algorithms. The actual reasoning. This is what separates engineers who build AI from operators who use it. Stanford charged $60,000 a year for students to sit in this classroom. They put the whole thing on YouTube. Bookmark this before you open any other AI resource today.

CyrilXBT

18,550 views • 7 days ago

PEDOGATE 2020 HD | In-Depth Exploration A reupload of part one in a three-part series (although I never set out to make a series, so technically this video can serve as a standalone) that outlines the satanic headquarters in Washington DC, awful algorithms on YouTube and what happens to a human soul that gives in to sin and temptation. Most of this video is theoretical, however some of it is purely evidence based, and none of this video is or ever was created with intent to harm. On the contrary, this video helps people follow Christ and his church. It serves to help the world through improving problematic imagery on search engines. And it holds the powerful accountable to the highest standard. That of Christ, who said, “See that you do not despise one of these little ones”. He also says that those who cause children to stumble will be punished. Since this video was made in 2020 the same issues are no longer present among these search engines or on the algorithms on YouTube. This is a good thing and needs to be celebrated. But let us never forget where the evil was on the internet. And how I found it by accident, bringing everyone along for the ride. More than ever this video needs to be seen. Enjoy. And share. Christ is KING 🇻🇦🇻🇦🇻🇦🇻🇦

Sensitive content

PEDOGATE 2020 HD | In-Depth Exploration A reupload of part one in a three-part series (although I never set out to make a series, so technically this video can serve as a standalone) that outlines the satanic headquarters in Washington DC, awful algorithms on YouTube and what happens to a human soul that gives in to sin and temptation. Most of this video is theoretical, however some of it is purely evidence based, and none of this video is or ever was created with intent to harm. On the contrary, this video helps people follow Christ and his church. It serves to help the world through improving problematic imagery on search engines. And it holds the powerful accountable to the highest standard. That of Christ, who said, “See that you do not despise one of these little ones”. He also says that those who cause children to stumble will be punished. Since this video was made in 2020 the same issues are no longer present among these search engines or on the algorithms on YouTube. This is a good thing and needs to be celebrated. But let us never forget where the evil was on the internet. And how I found it by accident, bringing everyone along for the ride. More than ever this video needs to be seen. Enjoy. And share. Christ is KING 🇻🇦🇻🇦🇻🇦🇻🇦

Mouthy Buddha

122,290 views • 1 year ago

STANFORD JUST PUT ITS ENTIRE ARTIFICIAL INTELLIGENCE CURRICULUM ON YOUTUBE FOR FREE. CS221. The same course that produced engineers now running AI labs, building frontier models, and getting paid $500,000 a year at the companies everyone is trying to work for. Most people have never heard of it. The ones who have are not telling you about it. Here is what the course actually covers: Search algorithms. The mathematical foundation behind every AI that finds optimal solutions in complex environments. Constraint satisfaction. How AI reasons through problems with thousands of interdependent variables simultaneously. Markov decision processes. The probabilistic framework behind every AI agent that makes sequential decisions under uncertainty. Machine learning from first principles. Not how to use sklearn. How the math actually works underneath it. Neural networks. Built from the ground up before jumping to applications. Logic and knowledge representation. How AI systems reason about the world formally. Natural language processing. The foundation of everything happening in LLMs right now. Robotics and computer vision. How AI perceives and acts in physical environments. Every concept that powers every AI product you use daily is in this curriculum. Not a surface level overview. The actual mathematics. The actual algorithms. The actual reasoning. This is what separates engineers who build AI from operators who use it. Stanford charged $60,000 a year for students to sit in this classroom. They put the whole thing on YouTube. Bookmark this before you open any other AI resource today. Follow CyrilXBT for more elite resources that build real depth the moment they drop.

STANFORD JUST PUT ITS ENTIRE ARTIFICIAL INTELLIGENCE CURRICULUM ON YOUTUBE FOR FREE. CS221. The same course that produced engineers now running AI labs, building frontier models, and getting paid $500,000 a year at the companies everyone is trying to work for. Most people have never heard of it. The ones who have are not telling you about it. Here is what the course actually covers: Search algorithms. The mathematical foundation behind every AI that finds optimal solutions in complex environments. Constraint satisfaction. How AI reasons through problems with thousands of interdependent variables simultaneously. Markov decision processes. The probabilistic framework behind every AI agent that makes sequential decisions under uncertainty. Machine learning from first principles. Not how to use sklearn. How the math actually works underneath it. Neural networks. Built from the ground up before jumping to applications. Logic and knowledge representation. How AI systems reason about the world formally. Natural language processing. The foundation of everything happening in LLMs right now. Robotics and computer vision. How AI perceives and acts in physical environments. Every concept that powers every AI product you use daily is in this curriculum. Not a surface level overview. The actual mathematics. The actual algorithms. The actual reasoning. This is what separates engineers who build AI from operators who use it. Stanford charged $60,000 a year for students to sit in this classroom. They put the whole thing on YouTube. Bookmark this before you open any other AI resource today. Follow CyrilXBT for more elite resources that build real depth the moment they drop.

CyrilXBT

54,956 views • 4 months ago

Lina Khan: "The holy grail for companies for a long time has been the ability to charge each person what their willingness to pay is. If you're really hungry for lunch, maybe they'll charge you 10 bucks for a burger, but if you're not that hungry, maybe they'll charge you three bucks... Now there's so much data collected about individual people that there is a serious worry that companies will be able to do this. And actually Delta Airlines just announced on their earnings call that they're gonna start using some of these algorithms to price some of their tickets. And so imagine a world in which you have the death in the family. You have to go home for a funeral. And they know that through scraping your email that is announcing when the service is gonna be, they know you're in a tight spot. So you're gonna be charged much more because of that." Watch the full Lina Khan Episode of Lemonade Stand here:

Lina Khan: "The holy grail for companies for a long time has been the ability to charge each person what their willingness to pay is. If you're really hungry for lunch, maybe they'll charge you 10 bucks for a burger, but if you're not that hungry, maybe they'll charge you three bucks... Now there's so much data collected about individual people that there is a serious worry that companies will be able to do this. And actually Delta Airlines just announced on their earnings call that they're gonna start using some of these algorithms to price some of their tickets. And so imagine a world in which you have the death in the family. You have to go home for a funeral. And they know that through scraping your email that is announcing when the service is gonna be, they know you're in a tight spot. So you're gonna be charged much more because of that." Watch the full Lina Khan Episode of Lemonade Stand here:

More Perfect Union

171,665 views • 1 year ago