Sitemap - 2024 - Shchegrikovich LLM

How do you choose an AI Agent as a business user?

Three ways to evaluate AI Agents

Creating an embedding model

In search of the meaning of everything or best-in-class embedding models right now

Chasing OpenAI's o1 one month later

How and why does CoT work?

Two methods and Prolog to increase trust of LLM solutions

Reducing hallucinations in LLMs using probabilities

Game development in LLM-era

Use computers like it's 1972, but this time with LLMs

Your AI Agent needs a new brain - Large Action Model

Use Prolog to improve LLM's reasoning

New approaches in RLHF

Time to replace Large Language Models or why o1 is a big deal

Autonomous AI agents with self-improvement capabilities

Language Models and software developers

How to use LLM-judge?

From zero to hero in LLM apps

Where is RAG architecture going?

RouteLLM to the rescue

How to build a search assistant?

How do Large Language Models stop unsafe content?

Llama 3 report Q&A

Why it's hard to train a model like Llama 3 405B?

Is it possible to detect Gen AI text?

On the way to solve the hardest problem with LLMs - Medical AI

The Best Planning Practices for AI Agents

How to do a data analysis with LLM?

How to write a perfect prompt?

All attentions in one place is all you need

How do LLMs help in research and innovation?

Low-level optimisations in Attention or why some LLM apps work faster than others

How to choose embeddings model for your LLM app?

What do all these layers do in LLM?

When 1-bit is enough for LLM

Measuring RAG systems in LLM applications

LLMs coming to mobile

Three options for information extraction with LLMs

LLM - from the next token prediction to meaningful answers

Mamba as an alternative architecture to LLM Transformers

Generating high quality content with LLMs

How do you create your own LLM and win The Open LLM Leaderboard with one Yaml file?

The GenAI world can be tricky to understand. Numbers add a new perspective.

LLMs in highly specialized domains

Reducing cost of software development with Code LLMs

Debugging RAG systems

State of GUI Agents

Zoo of RAGs

Mixture of Experts. The magic behind Mixtral models

RNN vs Transformers or how scalability made possible Generative AI?

What is actually sent to the LLM?

The power of small LLMs.

Why does Microsoft use DSL to build copilot, and how can you do the same in your GenAI app?