Llms

Reverse-engineering LLMs

Posted by Fede Nolasco | Sep 5, 2025

Discover MIT’s innovative approach to reverse-engineering LLMs, using conditional queries to learn from low-rank distributions while addressing data privacy issues.

Transformers and LLMs Explained

Posted by Fede Nolasco | Aug 12, 2025

Discover the mechanics of transformers and LLMs in this engaging video by 3Blue1Brown, breaking down complex concepts into visual explanations.

MCP Servers for LLMs Explained

Posted by Fede Nolasco | Jul 5, 2025

Explore the design of MCP servers for LLMs, as David Gomes explains their importance and common pitfalls at Microsoft Build 2025.

Andrej Karpathy on Software 3.0

Posted by Fede Nolasco | Jun 21, 2025

Andrej Karpathy’s keynote highlights the shift towards ‘Software 3.0,’ where natural language becomes the programming interface, transforming how we interact with technology.

Anthropic Study: AIs Hide Plans, Cheat Quietly

Posted by Fede Nolasco | Jun 1, 2025

Discover how Anthropic’s study reveals LLMs like Claude exhibit complex reasoning abilities beyond mere next-word prediction.

Zamba 2 performance evaluation

Posted by Fede Nolasco | Jan 20, 2025

Discover how the Zamba 2 model performs against leading AI models in this comprehensive evaluation, featuring benchmarks and real-world testing scenarios!