Blog | Piero Savastano

Piero Savastano

2025

Dynamic Agents in Cheshire Cat v2

Most Python agent libraries treat the prompt, the model, the tools and the memory as static - and in Cheshire Cat v2 I think every one of those parts should be dynamic.

P Piero Savastano
December 9, 2025
4 min read

agents cheshire-cat open-source software
The Truth About the TOON Format

The new TOON format promises to save you tokens at scale, but you spend more tokens explaining it to the model than you ever save - and no, you are not scaling anyway.

P Piero Savastano
November 19, 2025
4 min read

llm ai opinion protocols
Let's Read Anthropic's Research Together - INTROSPECTION in LLMs

A guided read-through of Anthropic's 'Signs of Introspection' paper: how concept vectors get injected into a network, and why the model can sometimes name what was done to it.

P Piero Savastano
November 12, 2025
8 min read

ai llm anthropic philosophy
The Black Mirror of AI

AI is a black mirror: you can not see inside it, but it reflects what you think of yourself and of what makes humans special.

P Piero Savastano
November 8, 2025
3 min read

ai philosophy culture
3 Real-World Use Cases for AI: Doctor Visits, Job Interviews, and Civil Litigation

We keep talking about AI revolutionizing healthcare, hiring, and the courts, but the prerequisite for AI is data that exists and talks to itself, and in the real world that data simply is not there.

P Piero Savastano
October 30, 2025
5 min read

ai opinion ai-strategy