Summary
This video explains seven key AI terms like AI agents, vector databases, and artificial superintelligence (ASI). It shows how these technologies work and why they matter today and in the future. The speaker also invites viewers to an upcoming IBM AI event to learn more.
Highlights
id996681515
large reasoning models. Now, these are specialized LLMs that have undergone reasoning-focused fine tuning. So, unlike regular LLMs that generate responses immediately, reasoning models, they’re trained to work through problems step by step, which is exactly what agents need when planning complex, multistep tasks. Now, the reasoning model is trained on problems with verifiably correct answers. So, math problems or code that can be tested by compilers and through reinforcement learning, the model learns to generate reasoning sequences that lead to correct final answers. So, every time you see a chatbot pause Before it responds back to you by saying, thinking, well, that’s the reasoning model at work, generating an internal chain of thought to break down a problem step by step before generating a response.
Escuché alguna vez por ahí que estos modelos son LLM que se entrenan adicionalmente con problemas matemáticos, lo mismo que dice aquí, pero nunca lo he verificado. Necesito estudiar más la historia del nacimiento de estos modelos para entenderlo mejor.
id996681844
in a vector database, we don’t store raw data like text files and like images, just as blobs of data. We actually use something called an embedding model. And that embedding model is used to convert that data from these images here into actually a vector. Now, what is a vector? Well, a vector is essentially just kind of a long list of numbers. And that long list of numbers captures the semantic meaning of the context. Now, what’s the benefit of doing that? Well, in a vector database, we can perform searches as mathematical operations, looking for vector embeddings that are close to each other. And that translates to finding semantically similar content.
Vector database, embedding model y vectores son conceptos bien relacionados que tengo que entender más
id996681955
RAG makes use of these vector databases. And it uses it to enrich prompts to an LLM. So, we start here with a RAG retriever component. Now that might take in an input prompt from a user. And it’s going to turn it into a vector using an embedding model. That’s the thing that ties it into that series of numbers. And then, once we’ve done that, we can perform a similarity search in the vector database. Now that vector database will return something, And we’ll return that all the way back to the large language model prompt that we started with. And we’ll embed into that prompt now the stuff that came out of that vector database. So, I can ask a question about let’s say company policy. And then this RAG system is going