PinnedSergey ShchegrikovichHow to improve GenAI app value by knowing the difference between coney and rabbit?A coney is a synonym for a rabbit, but out of use today. If you google for a coney you will get this answer and the same correct response…Dec 15, 2023Dec 15, 2023
Sergey ShchegrikovichMixture of Experts. The magic behind Mixtral modelsIn the last post https://www.linkedin.com/feed/update/urn:li:activity:7157437022553427968/, I described the difference between RNN and…Feb 4Feb 4
Sergey ShchegrikovichRNN vs Transformers or how scalability made possible Generative AI?LLMs are built on top of the Transformer architecture, but before Transformers, the leading architecture for building NLP apps was…Jan 28Jan 28
Sergey ShchegrikovichWhat is actually sent to the LLM?This week, Stable LM 2 1.6B was released by Stability.ai, and to use it properly, the instruction format was shared.Jan 21Jan 21
Sergey ShchegrikovichThe power of small LLMsPhi2 from Microsoft has got 220K downloads on HuggingFace and it makes Phi2 one of the most popular language models.Jan 13Jan 13
Sergey ShchegrikovichWhy does Microsoft use DSL to build copilot, and how can you do the same in your GenAI app?I like this video from the Ignite conference — “How Microsoft 365 Copilot works | BRK256”. In the video, you can find the process and…Jan 4Jan 4
Sergey ShchegrikovichAttacks against LLM-based apps and how to prevent themApps based on LLMs and AI Agents require different threat modelling and prevention compared to standard web or mobile apps. Some attacks…Dec 27, 2023Dec 27, 2023
Sergey ShchegrikovichHow do AI Agents think?There are three strategies to implement thinking capabilities into AI Agents for GenAI apps.Dec 24, 2023Dec 24, 2023