Piero Savastano

Posts tagged with

llm

Already Out of Tokens?

Why usage of non-American models is exploding, what you actually save, and the catch nobody mentions.

P Piero Savastano
July 7, 2026
3 min read

llm open-models cost claude
The Truth About Fable, After the Ban

The Mythos-to-Fable hype cycle, the ban, and the compute economics that quietly make these models dumber.

P Piero Savastano
July 3, 2026
7 min read

ai anthropic llm surveillance
The 3 Loops of AI: Token, Tool, and Task

The word "loop" gets thrown around a lot in AI - but there are at least three nested ones, from single tokens up to whole tasks.

P Piero Savastano
June 10, 2026
4 min read

agents context-engineering llm mcp
Fable 5 and Agents in a Loop

Fable 5 finally ships, and top agent builders now write loops instead of prompts - at a steep token cost.

P Piero Savastano
June 9, 2026
4 min read

fable agents llm
How to Sell AI Agents: The Main Obstacle

The hardest part of selling AI is getting people who expect exactness from a computer to accept that a statistical model is uncertain by definition - and to design around that.

P Piero Savastano
April 29, 2026
6 min read

agents consulting ai-strategy llm
Old Age Teaches: From GPT-2 to Mythos

The "too dangerous to release" routine is not new: OpenAI already played that card with GPT-2, and it is a magic trick to lure the gullible, not a safety measure.

P Piero Savastano
April 14, 2026
2 min read

ai llm opinion anthropic
From GPT-3 (2020) to Claude Code (2026) - Easy Whiteboard Explanation

A whiteboard walk through the three big jumps that took us from a language model to an agent: GPT-3, ChatGPT, and Claude Code.

P Piero Savastano
March 26, 2026
7 min read

ai llm agents agentic-coding
AI Agents Are Simply Software

The language model is stateless: it takes context in and spits one token out. An agent is just the software you wrap around it to give it memory and actions. Everything else follows from that.

P Piero Savastano
January 5, 2026
7 min read

agents ai llm 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
How to Get Started with AI? Is It Worth It?

It is worth it precisely because everything is still fragmented and uncertain, and here is the concrete path in: mess with the online services, then learn context, memory and tools.

P Piero Savastano
October 16, 2025
8 min read

ai agents llm cheshire-cat
What Is an AI AGENT

A plain-language explainer: an agent is software that wraps a language model, building the prompt with retrieved context and tools and interpreting the response before it reaches you.

P Piero Savastano
August 9, 2025
7 min read

agents llm ai mcp
August 7, 2025

My hot take on the GPT-5 launch: incremental additions, a cringe-worthy live demo, and the clearest sign yet that OpenAI has stopped innovating.

P Piero Savastano
August 7, 2025
3 min read

ai llm opinion anthropic
How to Make Estimates with AI

Why I keep refusing to build fully automatic quoting systems: language models do not do math, and the real business rules live as implicit knowledge in human heads.

P Piero Savastano
August 1, 2025
6 min read

ai llm consulting ai-strategy
How Kenyans and Venezuelans Are Being Exploited by the AI Market

The reason ChatGPT is polite and safe is an invisible workforce of underpaid annotators in the poorest corners of the world, hunted for being educated and desperate.

P Piero Savastano
July 24, 2025
8 min read

ai ethics politics llm
Transformer and Attention in LLMs

What actually sits inside the black box of a language model: the Transformer architecture, attention blocks, and why language is just a time series to a machine.

P Piero Savastano
July 19, 2025
6 min read

ai llm
What Is RAG?

RAG sounds complicated, but the acronym already tells you everything: you retrieve relevant content and stuff it into the prompt so the model has the answer in front of it.

P Piero Savastano
July 16, 2025
4 min read

ai llm cheshire-cat
ChatGPT Is Like a COCKROACH

After a nighttime fight with a giant cockroach, a reflection on collective intelligence, embodiment, and why AI might be less a mind in a box and more a swarm-like form of artificial life.

P Piero Savastano
July 10, 2025
5 min read

ai philosophy llm
Guide to AI Basics

A plain-language tour of the terms you keep hearing: model, agent, RAG, MCP, GPUs and data centers, and the Cheshire Cat.

P Piero Savastano
July 6, 2025
8 min read

ai llm agents mcp