Sara Zan

Announcement, Colab.

This is a piece I wrote for The Byte, the AI Collective's Tuesday newsletter.

LLM reasoning has a simple appeal: give the model more room to think, and the answer should improve.

This is episode 9 of a series of shorter blog posts answering questions I received during the course of my work.

GPT-5.x models are reasoning models, and as such, you can set the reasoning effort that they should make when addressing your prompts.

Announcement, slides.

This post is a write-up of my talk at The Economist's Impact 2nd AI Compute Summit.

Announcement, Colab Notebook, archive folder.

Announcement, Colab Notebook, archive folder.

This is episode 8 of a series of shorter blog posts answering questions I received during the course of my work.

Announcement.

Slides.

This is episode 7 of a series of shorter blog posts answering questions I received during the course of my work.

This post is based on one of my talks, "Phishing AI Agents".

Announcement, recording, slides, demo repository and demo recording.

This is episode 6 of a series of shorter blog posts answering questions I received during the course of my work.

Announcement, interactive notebook, presentation.

For my workshop at the Agentic AI Summit I vibe-coded this small Jupyter Notebook widget on top of ipywidgets<8.0.0, for easy compatibility with Colab.

If you're interested in this topic, you can check out the Colab notebook as well. 2025 was the year of LLM reasoning.