Archive - Shchegrikovich LLM

Dynamic Sub Agents in Claude Code

Claude Code is one of the most popular AI assistants for software engineers.

Jul 27 •

Where to put Normalization Layer in Transformers?

There is an interesting change happening in recent models.

Jul 20 •

Truly open LLMs

To make an LLM a truly open one, one needs not only to publish weights but also data and training receipts.

Jul 13 •

Language Models Meet Diffusion

Auto-aggressive models dominate the LLM space.

Jul 6 •

June 2025

4 Architectures of Deep Research Agents

Deep Research is a feature of AI systems that helps users to do in-depth analysis of a selected topic.

Jun 29 •

RAG to improve application reasoning

The primary use case of RAG is to feed a model with information it does not have.

Jun 22 •

Mind the gap. Next stop - AI Lawyer

One of the high-potential areas for automation with LLMs is Law.

Jun 15 •

Evaluating Conversational AI Agents

Evaluation of prompts in the LLM world is hard; evaluation of conversational agents is even harder.

Jun 8 •

Improved planning for AI Agents

In June 2024, Google DeepMind released an interesting benchmark, Natural Plan.

Jun 1 •

May 2025

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts