Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

You see this SSRF attack yeah? Big companies with strong engineering teams like Capital One, GitHub, Microsoft, Alibaba, and others, have all suffered from it in the past. Once an attacker successfully exploits SSRF, they can pivot from the application into the underlying infrastructure, using credentials (keys, tokens, metadata...

commando_skiipz's profile picture

Ghost St Badmus

14,695 subscribers

92,794 Aufrufe • vor 9 Monaten •via X (Twitter)

Nachrichten & PolitikBildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Osmantic founder Ahmad warns companies relying on cloud AI are building on models that can be changed, slowed down, or taken away without them even knowing: "If you're using any quantity of tokens, you should start hosting your own LLMs. You don't know when a model is gonna change on you. APIs are always having this latest endpoint, so you always end up, it gets rug pulled from underneath you" "How could you tell if a certain country is getting 5, 10 IQ points drop in their inference from the cloud? You can't tell from the cloud. What I'm seeing from OpenAI is that they are making their models slower so that they can serve with the limited compute they have" "It has to be in the back of your mind, is your data safe? Is there a more efficient way to get quality tokens, cheaper alternatives, and something that is yours and you can own the infrastructure end to end?" Osmantic
1:52

Osmantic founder Ahmad warns companies relying on cloud AI are building on models that can be changed, slowed down, or taken away without them even knowing: "If you're using any quantity of tokens, you should start hosting your own LLMs. You don't know when a model is gonna change on you. APIs are always having this latest endpoint, so you always end up, it gets rug pulled from underneath you" "How could you tell if a certain country is getting 5, 10 IQ points drop in their inference from the cloud? You can't tell from the cloud. What I'm seeing from OpenAI is that they are making their models slower so that they can serve with the limited compute they have" "It has to be in the back of your mind, is your data safe? Is there a more efficient way to get quality tokens, cheaper alternatives, and something that is yours and you can own the infrastructure end to end?" Osmantic

MTS

15,040 Aufrufe • vor 21 Tagen

Building with AI gets easier every day. Here is an open-source library that makes integrating AI into an application extremely easy: Star the repository! This library alone can make React the best front-end framework out there! There are a bunch of cool things I like about CopilotKit. Here are 3 of them: 1. It allows you to take any -powered agent and bring it into your application. (This is a brand-new feature!) 2. You can build an AI-powered chatbot in your application. The chatbot will have access to your context and can act on the application. 3. You can build a RAG workflow to process and answer questions from a real-time knowledge base. I recorded a video to show you how simple it is to make some of this happen. A few lines of code, and you are in business. Here is a link to the sample application: CopilotKit is open-source. You can self-host it. You can use it with any LLM. Thanks to the team for showing me their tool and collaborating with me on this post!
5:59

Building with AI gets easier every day. Here is an open-source library that makes integrating AI into an application extremely easy: Star the repository! This library alone can make React the best front-end framework out there! There are a bunch of cool things I like about CopilotKit. Here are 3 of them: 1. It allows you to take any -powered agent and bring it into your application. (This is a brand-new feature!) 2. You can build an AI-powered chatbot in your application. The chatbot will have access to your context and can act on the application. 3. You can build a RAG workflow to process and answer questions from a real-time knowledge base. I recorded a video to show you how simple it is to make some of this happen. A few lines of code, and you are in business. Here is a link to the sample application: CopilotKit is open-source. You can self-host it. You can use it with any LLM. Thanks to the team for showing me their tool and collaborating with me on this post!

Santiago

108,884 Aufrufe • vor 2 Jahren

I really want to show off the cutting edge tech the team is building and how we're turning AI image generation into real living environments using gaussian splats and at the :19 mark of this video you can see how we're blending splats together to create a real world. What this looks like from a gaming perspective is this all happens behind the players view to simulate a real world environment. As you move through the space, distance becomes a variable to consider on how images update and are experienced. We are creating a new reality in real time.
1:21

I really want to show off the cutting edge tech the team is building and how we're turning AI image generation into real living environments using gaussian splats and at the :19 mark of this video you can see how we're blending splats together to create a real world. What this looks like from a gaming perspective is this all happens behind the players view to simulate a real world environment. As you move through the space, distance becomes a variable to consider on how images update and are experienced. We are creating a new reality in real time.

𝔹𝕃𝕍ℂ𝕂𝕃!𝔾ℍ𝕋

25,084 Aufrufe • vor 3 Monaten

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.
5:38

Web scraping is a critical skill, and yet nobody talks about it. How do you think companies are training their Large Language Models? Where do you think the data comes from? But web scraping goes beyond all of that. Imagine giving an AI agent access to any public online data in real time! I like to call this "web-scrapping on demand", and I'm pretty sure it's going to unlock unlimited power for AI applications. I recorded a quick video to show you how you can do this using Apify. I've talked about them before, and they are collaborating with me on this post. They have one of the best open-source web scraping and browser automation libraries out there: But it gets much better than this! You can use MCP to connect your AI Agents and applications to the Apify platform and use any specialized actor on demand to scrape and process online data. In the video, I used Cursor to scrape LinkedIn posts with the words "Machine Learning" in real time. Worked like a charm with no code needed! Here is a link to the platform: Think about this: You can now feed your AI applications with any public data on demand! We aren't ready for what's coming.

Santiago

101,473 Aufrufe • vor 1 Jahr

This is a standard practice for almost all Tier-1 banking applications in Nigeria, and for some fintech applications I’ve previously performed pentests on. Client-side encryption isn’t a total waste, or a waste of compute, as some people have claimed, but rather a measure to protect against API tampering or API request/response manipulation between the client and the server when implemented properly. Even with HTTPS, attackers can capture a decrypted version of web or mobile API data in transit because the browser and the server establish a level of trust during the TLS handshake. Attackers can leverage this trust to capture & proxy already-decrypted traffic, tamper with it, and then forward it to the server. This allows them to override what the user interface or client is originally supposed to send and replace it with data of their choosing. That is why validation needs to be performed on both the client and the server side. To wrap up, encrypting API requests and responses makes it significantly harder for attackers to tamper with data, even if they capture the traffic, unless they have access to the encryption details (algorithm, encryption mode, key size, secret key, and initialization vector), assuming asymmetric encryption is used. In the demo below, you can see how I discovered additional parameters (balance, is_admin) in the API response, captured the registration API request, despite it being sent over HTTPS from the interface, added the discovered parameters, and successfully inflated my balance to 50 billion and also escalated my privileges to admin, and ultimately deleted the accounts of two live users/customers. In the second slide, I captured an API traffic of a bank app, and you can see how difficult the payloads are to read.
2:38

This is a standard practice for almost all Tier-1 banking applications in Nigeria, and for some fintech applications I’ve previously performed pentests on. Client-side encryption isn’t a total waste, or a waste of compute, as some people have claimed, but rather a measure to protect against API tampering or API request/response manipulation between the client and the server when implemented properly. Even with HTTPS, attackers can capture a decrypted version of web or mobile API data in transit because the browser and the server establish a level of trust during the TLS handshake. Attackers can leverage this trust to capture & proxy already-decrypted traffic, tamper with it, and then forward it to the server. This allows them to override what the user interface or client is originally supposed to send and replace it with data of their choosing. That is why validation needs to be performed on both the client and the server side. To wrap up, encrypting API requests and responses makes it significantly harder for attackers to tamper with data, even if they capture the traffic, unless they have access to the encryption details (algorithm, encryption mode, key size, secret key, and initialization vector), assuming asymmetric encryption is used. In the demo below, you can see how I discovered additional parameters (balance, is_admin) in the API response, captured the registration API request, despite it being sent over HTTPS from the interface, added the discovered parameters, and successfully inflated my balance to 50 billion and also escalated my privileges to admin, and ultimately deleted the accounts of two live users/customers. In the second slide, I captured an API traffic of a bank app, and you can see how difficult the payloads are to read.

Ghost St Badmus

217,957 Aufrufe • vor 9 Monaten

ANTHROPIC JUST RELEASED A FREE 23-PAGE GUIDE THAT COMPANIES ARE PAYING $50,000 TO CONSULTANTS FOR. How to build Claude into your entire business infrastructure - 100% FREE. Most companies using AI in 2026 are doing the same thing. Anthropic explains what real enterprise AI infrastructure actually looks like. Not marketing, not a sales deck, just a practical guide from the people who build these systems. What is inside: ↳ How to move Claude from a chat tool to core business infrastructure ↳ How to connect it to your internal databases and live documents ↳ How to design automated workflows for your exact processes ↳ How to handle institutional data safely at scale The most important line in the whole document: The model alone is not enough. The value is in how it connects to your systems, data, and workflows. Save this.
0:26

ANTHROPIC JUST RELEASED A FREE 23-PAGE GUIDE THAT COMPANIES ARE PAYING $50,000 TO CONSULTANTS FOR. How to build Claude into your entire business infrastructure - 100% FREE. Most companies using AI in 2026 are doing the same thing. Anthropic explains what real enterprise AI infrastructure actually looks like. Not marketing, not a sales deck, just a practical guide from the people who build these systems. What is inside: ↳ How to move Claude from a chat tool to core business infrastructure ↳ How to connect it to your internal databases and live documents ↳ How to design automated workflows for your exact processes ↳ How to handle institutional data safely at scale The most important line in the whole document: The model alone is not enough. The value is in how it connects to your systems, data, and workflows. Save this.

Kanika

16,545 Aufrufe • vor 3 Monaten

🚨This is how you turn a crash into a great depression. This is a public bailout of the worst bubble in history. “It’s a concept out there that’s so much money and it’s so big… where the American public essentially becomes a partner with the companies… the American people can benefit from the success of AI and by doing that they’re going to like it better…”
0:54

🚨This is how you turn a crash into a great depression. This is a public bailout of the worst bubble in history. “It’s a concept out there that’s so much money and it’s so big… where the American public essentially becomes a partner with the companies… the American people can benefit from the success of AI and by doing that they’re going to like it better…”

Jim Stewartson, Decelerationist 🇨🇦🇺🇦🇺🇸

119,370 Aufrufe • vor 3 Monaten

made a big breakthrough on tinynodes! this is a huge .blend file with 679 nodes, running 100% in the browser... and it's fully dynamic! at the end of the video, you can see the raw geometry and the node graph that describes how to turn it into this complex wooden structure
0:24

made a big breakthrough on tinynodes! this is a huge .blend file with 679 nodes, running 100% in the browser... and it's fully dynamic! at the end of the video, you can see the raw geometry and the node graph that describes how to turn it into this complex wooden structure

Seth Thompson

36,436 Aufrufe • vor 4 Monaten

This is very true. AI integration is both hard and necessary for companies. And AI-native junior employees can drive this adoption. Earlier this year Aaron Levie explained with martin_casado on the a16z podcast how AI fluency is one of the most powerful skills a new grad can have. The real value comes from knowing how to make AI work inside an organization. Most companies, both large and small, are slow to adopt new technology. They need people who can explain what AI can do, show them how to use it, and help them move faster. If you are fluent in AI, you can be that person. You can walk into a company, spot the areas where AI can save time or create new opportunities, and make it happen. That is a wedge into your first job and a way to stand out from everyone else.
0:39

This is very true. AI integration is both hard and necessary for companies. And AI-native junior employees can drive this adoption. Earlier this year Aaron Levie explained with martin_casado on the a16z podcast how AI fluency is one of the most powerful skills a new grad can have. The real value comes from knowing how to make AI work inside an organization. Most companies, both large and small, are slow to adopt new technology. They need people who can explain what AI can do, show them how to use it, and help them move faster. If you are fluent in AI, you can be that person. You can walk into a company, spot the areas where AI can save time or create new opportunities, and make it happen. That is a wedge into your first job and a way to stand out from everyone else.

a16z

366,027 Aufrufe • vor 1 Jahr

I was just messing around with the animation, then I noticed that the swimming animation would leave the ripple effect behind, and you can change the size of it, too And of course, you can do this even on a land surface (Imagine a scene with you standing on land, but have a water ripple effect, something like that) Also, in this video, I just learn how to use the sky environment It's really helped me a lot to find the perfect cloud and sky color And I'm really proud of what the final picture has turned into #GPOSER #GPOSERS
1:09:07

I was just messing around with the animation, then I noticed that the swimming animation would leave the ripple effect behind, and you can change the size of it, too And of course, you can do this even on a land surface (Imagine a scene with you standing on land, but have a water ripple effect, something like that) Also, in this video, I just learn how to use the sky environment It's really helped me a lot to find the perfect cloud and sky color And I'm really proud of what the final picture has turned into #GPOSER #GPOSERS

Lightny Lightningstorm

12,525 Aufrufe • vor 7 Monaten

How to Create Music That Matches Your Video's Sound with Suno Studio I made a quick video showing how I use Suno Studio to generate background music that fits the audio and mood of a video, similar to the example in the quoted post. This is the method I use at the moment but if you have a better approach, feel free to share it. Before starting, export the original audio from your video. I usually do this in CapCut. After generating a track you like in Suno Studio, you can import it back into CapCut and add it to your video. *This is not a paid partnership.
1:42

How to Create Music That Matches Your Video's Sound with Suno Studio I made a quick video showing how I use Suno Studio to generate background music that fits the audio and mood of a video, similar to the example in the quoted post. This is the method I use at the moment but if you have a better approach, feel free to share it. Before starting, export the original audio from your video. I usually do this in CapCut. After generating a track you like in Suno Studio, you can import it back into CapCut and add it to your video. *This is not a paid partnership.

Kōda

37,597 Aufrufe • vor 3 Monaten

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.
8:15

Here is how you can install an open-source, enterprise-grade RAG system on your server (with the best document understanding I've seen.) First, something obvious to anyone trying to sell RAG in the market: You are crazy if you think companies will let their data travel to a hosted model. No one wants to send their data anywhere (those who do haven't found an alternative.) Every single company would rather have an air-gapped system with no internet access. GroundX is an open-source RAG system that you can run on your servers (or any cloud provider, as long as you have access to GPUs) and works without a network. (If the military wants to do RAG, this is precisely what they will be looking for.) I installed GroundX on my AWS account and recorded a video to show you how to use it. There are two services you can use: 1. Ingest: This service uses a pretrained vision model to ingest and understand your knowledge base. 2. Search: This service combines text and vector search with a fine-tuned re-ranker model to retrieve information from your knowledge base. A quick note about the Ingest service: 99% of people think they need better "retrieval" mechanisms. I think they need better "ingestion." That's where this service comes in! Ingest "understands" your documents in a way I haven't seen before. After you try it, you'll realize why showing your LLM your raw documents is a bad idea. In the video, I use a free tool called X-Ray to test a document and understand how the Ingest service breaks it down. You can access this tool by signing up for a free GroundX cloud account and uploading your documents. You'll see a bit more about this in the video.

Santiago

89,664 Aufrufe • vor 1 Jahr

You can't pretend you care about security if you are still sharing API tokens in .env files or sharing SSH keys. This might be good enough to provide simple access to a resource, but it's a horrible way to do security when it really matters. Look into "Identity-Based Access". The state of the art today is Identity-Based Access. With traditional security, you have to present a key to get access to the resource (an API key, a password, or an SSH key). These are long-lived keys you need to keep secret somehow. If somebody steals your key, they become you and get the same access you had. With Identity-Based Access, you need to prove who you are instead. If you are a human, you can prove this with a passkey, SSO with Google or GitHub, or Multi-Factor Authentication. If you are a computer, you can use AWS IAM, Kubernetes, a cloud service account, or any other trusted environment. Once the system verifies your identity, it checks your permissions and gives you a short-lived credential. Prove identity → Permissions → Short-lived credential → Access The difference here is huge, because those credentials are: • Short-lived • Tied to a specific identity • Scoped to specific permissions • Automatically expired • Much easier to audit In practice, implementing this is as simple as integrating with Teleport, which will handle everything for you. Here is a full explanation of how Teleport works and how you can start using it: Thanks to the Teleport team for partnering with me on this post.
5:46

You can't pretend you care about security if you are still sharing API tokens in .env files or sharing SSH keys. This might be good enough to provide simple access to a resource, but it's a horrible way to do security when it really matters. Look into "Identity-Based Access". The state of the art today is Identity-Based Access. With traditional security, you have to present a key to get access to the resource (an API key, a password, or an SSH key). These are long-lived keys you need to keep secret somehow. If somebody steals your key, they become you and get the same access you had. With Identity-Based Access, you need to prove who you are instead. If you are a human, you can prove this with a passkey, SSO with Google or GitHub, or Multi-Factor Authentication. If you are a computer, you can use AWS IAM, Kubernetes, a cloud service account, or any other trusted environment. Once the system verifies your identity, it checks your permissions and gives you a short-lived credential. Prove identity → Permissions → Short-lived credential → Access The difference here is huge, because those credentials are: • Short-lived • Tied to a specific identity • Scoped to specific permissions • Automatically expired • Much easier to audit In practice, implementing this is as simple as integrating with Teleport, which will handle everything for you. Here is a full explanation of how Teleport works and how you can start using it: Thanks to the Teleport team for partnering with me on this post.

Santiago

20,971 Aufrufe • vor 1 Monat

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.
3:27

English is the most powerful language in the world. MongoDB just added support for MCP, and literally anyone can now query data without knowing anything about databases. If you know English, you are all set. I recorded a quick video to show you how I connect to a sample Airbnb database and run different queries: • How many listings? • How many listings in the US? • What's the list of countries in these listings? It takes 10 seconds to configure Claude, Cursor, WindSurf, or any other AI assistant to connect to MongoDB's MCP Server. By the way, the server supports much more than queries: • You can explore your collections • You can fetch schema information • You can generate app code snippets • You can manage your databases • You can handle cluster/user/admin tasks Here is a link to the MCP server GitHub repository: This is huge for developers. It's even bigger for non-developers. Thanks to the MongoDB team for collaborating with me on this post.

Santiago

44,855 Aufrufe • vor 1 Jahr

Lightspeed's Bucky Moore says the real opportunity in the AI app layer is in large industries far enough afield from where the model providers are today — and where the context engineering to get customer data into the model is extremely nuanced and messy. "I think this is kind of the elephant in the room right now — whether post-training open-source models combined with the unique user feedback you get from being an application provider is defensible enough." "That is going to be an inevitable challenge for any of these industries that hit a maturation point of AI adoption, like legal and software engineering have." "But on the other hand, there are some industries where they're very large, they're far enough afield from where the model providers are today — and probably will continue to be — and the context engineering to actually get the customer data into the model is just so messy. It requires going across different business functions, it requires a lot of hands-on forward-deployed engineering." "Those are the kind of companies that we get really excited about. Because I think being really good at that is not only defensible, but it also allows you to generate a feedback loop with your customers, where you hear a lot of their secrets. And those secrets allow you to feed that back into how you make your product better at the expense of anyone else playing in the space. Because if you're serving the customer, they're only serving you those secrets." "I think Palantir is a good example of this in the pre-AI era, and I think we're going to see many companies ascend in that same way."
2:28

Lightspeed's Bucky Moore says the real opportunity in the AI app layer is in large industries far enough afield from where the model providers are today — and where the context engineering to get customer data into the model is extremely nuanced and messy. "I think this is kind of the elephant in the room right now — whether post-training open-source models combined with the unique user feedback you get from being an application provider is defensible enough." "That is going to be an inevitable challenge for any of these industries that hit a maturation point of AI adoption, like legal and software engineering have." "But on the other hand, there are some industries where they're very large, they're far enough afield from where the model providers are today — and probably will continue to be — and the context engineering to actually get the customer data into the model is just so messy. It requires going across different business functions, it requires a lot of hands-on forward-deployed engineering." "Those are the kind of companies that we get really excited about. Because I think being really good at that is not only defensible, but it also allows you to generate a feedback loop with your customers, where you hear a lot of their secrets. And those secrets allow you to feed that back into how you make your product better at the expense of anyone else playing in the space. Because if you're serving the customer, they're only serving you those secrets." "I think Palantir is a good example of this in the pre-AI era, and I think we're going to see many companies ascend in that same way."

TBPN

46,886 Aufrufe • vor 6 Monaten

Why aren't more people talking about how difficult it is to turn documents into structured data? This is literally a problem that every single company I talk to is trying to solve. They have a buttload of documents with forms and tables, and they want to turn them into usable data. Let me show you how you can do this using Tensorlake. Probably the best parser I've found:
6:41

Why aren't more people talking about how difficult it is to turn documents into structured data? This is literally a problem that every single company I talk to is trying to solve. They have a buttload of documents with forms and tables, and they want to turn them into usable data. Let me show you how you can do this using Tensorlake. Probably the best parser I've found:

Santiago

46,413 Aufrufe • vor 1 Jahr

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.
4:50

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,573 Aufrufe • vor 3 Jahren

I built this on-chain fund in 2 minutes. Deposits 50% into Morpho 🦋 Steakhouse USDG, uses the yield profit to DCA into $SLV AND $SPY. Uses 20% to buy ethereum:native and 30% to buy $AMZN Hit publish. Others can deposit in it. You can earn from the strategy and from user fees. This is what composable finance looks like. If you signed up for closed early access you can now try it at
0:43

I built this on-chain fund in 2 minutes. Deposits 50% into Morpho 🦋 Steakhouse USDG, uses the yield profit to DCA into $SLV AND $SPY. Uses 20% to buy ethereum:native and 30% to buy $AMZN Hit publish. Others can deposit in it. You can earn from the strategy and from user fees. This is what composable finance looks like. If you signed up for closed early access you can now try it at

gabidev

12,417 Aufrufe • vor 1 Monat