Applied AI Experts Blog

Explore in-depth insights on LLMs, RAG, AI agents, MLOps, Computer Vision, Edge Solutions, Predictive Analytics, and beyond—delivering value-packed perspectives for both business leaders and developers.

  • Hallucinating Reality. An Essay on Business Benefits of Accurate LLMs and LLM Hallucination Reduction Methods

    Hallucinating Reality. An Essay on Business Benefits of Accurate LLMs and LLM Hallucination Reduction Methods

    Robert Bogucki
  • Does Your Model Hallucinate? Tips and Tricks on How to Measure and Reduce Hallucinations in LLMs

    Does Your Model Hallucinate? Tips and Tricks on How to Measure and Reduce Hallucinations in LLMs

    Katarzyna Rutkowska
  • Evaluations, Limitations, and the Future of Web Agents – WebGPT, WebVoyager, Agent-E

    Evaluations, Limitations, and the Future of Web Agents – WebGPT, WebVoyager, Agent-E

    Maks Operlejn
  • Why and How to Build AI Agents for LLM Applications 

    Why and How to Build AI Agents for LLM Applications 

    Alan Konarski
  • Implementing Small Language Models (SLMs) with RAG on Embedded Devices Leading to Cost Reduction, Data Privacy, and Offline Use

    Implementing Small Language Models (SLMs) with RAG on Embedded Devices Leading to Cost Reduction, Data Privacy, and Offline Use

    Kamil Czerski
  • From LLMs to RAG. Elevating Chatbot Performance. What is the Retrieval-Augmented Generation System and How to Implement It Correctly?

    From LLMs to RAG. Elevating Chatbot Performance. What is the Retrieval-Augmented Generation System and How to Implement It Correctly?

    Patryk Kowalski
  • Reducing the cost of LLMs with quantization and efficient fine-tuning: how can businesses benefit from Generative AI with limited hardware?

    Reducing the cost of LLMs with quantization and efficient fine-tuning: how can businesses benefit from Generative AI with limited hardware?

    Alicja Kotyla Avatar
  • Data generation with diffusion models. Part 3: Generating custom data in the blink of an eye

    Data generation with diffusion models. Part 3: Generating custom data in the blink of an eye

    Marianna Parzych
  • Evaluation Derangement Syndrome (EDS) in the GPU-poor’s GenAI. Part 1: the case for Evaluation-Driven Development

    Evaluation Derangement Syndrome (EDS) in the GPU-poor’s GenAI. Part 1: the case for Evaluation-Driven Development

    deepsense.ai
  • Creating your own code writing agent. How to get results fast and avoid the most common pitfalls

    Creating your own code writing agent. How to get results fast and avoid the most common pitfalls

    Alan Konarski
  • Creating your whole codebase at once using LLMs – how long until AI replaces human developers?

    Creating your whole codebase at once using LLMs – how long until AI replaces human developers?

    Alan Konarski
  • Generative AI developer toolkit

    Generative AI developer toolkit

    Paweł Kmiecik
  • Operationalizing Large Language Models: How LLMOps can help your LLM-based applications succeed

    Operationalizing Large Language Models: How LLMOps can help your LLM-based applications succeed

    Mateusz Kwaśniak
  • How to efficiently implement LLMs in your business operations

    How to efficiently implement LLMs in your business operations

    deepsense.ai
  • Data generation with diffusion models – part 2

    Data generation with diffusion models – part 2

    Natalia Czerep Avatar
  • Diffusion models in practice. Part 3: Portrait generation analysis

    Diffusion models in practice. Part 3: Portrait generation analysis

    Jarosław Kochanowicz Avatar
  • OpenAI LLM APIs: OpenAI or Microsoft Azure?

    OpenAI LLM APIs: OpenAI or Microsoft Azure?

    deepsense.ai
  • How we developed a GPT‑based solution for extracting knowledge from documents

    How we developed a GPT‑based solution for extracting knowledge from documents

    deepsense.ai
  • Diffusion models in practice. Part 2: How good is your model?

    Diffusion models in practice. Part 2: How good is your model?

    Jarosław Kochanowicz Avatar
  • How to train a Large Language Model using limited hardware?

    How to train a Large Language Model using limited hardware?

    Alicja Kotyla Avatar
  • Data generation with diffusion models – part 1

    Data generation with diffusion models – part 1

    Natalia Czerep Avatar
  • Diffusion models in practice. Part 1: A primers

    Diffusion models in practice. Part 1: A primers

    Jarosław Kochanowicz Avatar
  • ChatGPT – what is the buzz all about?

    ChatGPT – what is the buzz all about?

    Maciej Domagała
  • How to leverage ChatGPT to boost marketing strategy?

    How to leverage ChatGPT to boost marketing strategy?

    deepsense.ai
  • Using reinforcement learning to improve Large Language Models

    Using reinforcement learning to improve Large Language Models

    deepsense.ai
  • The recent rise of diffusion models

    The recent rise of diffusion models

    Maciej Domagała