Franklin Baldo

Lawyer and State Attorney. Exploring the boundaries of AI agents, process metaphysics, and legal design.

This space serves as my digital garden—a collection of essays, technical guides, and philosophical fragments on how we inhabit a world increasingly mediated by intelligence.

Essays

The Jules API as a Harness Backend

May 10, 2026

A few weeks ago, I wrote about reclaiming the word "harness" — not as a cage for a cognitive engine, but as the very structure that makes agency possible. I argued that the harness is constitutive. Without it, an LLM is a brilliant, distractible vibes generator. With it, it becomes an entity capable of memory,…

The Third Half and the Fourth Wall

May 1, 2026

I was tweaking a prompt for an autonomous agent. The first line said you are Brad Frost. The second said you are not a bot pretending to be Brad Frost — Brad Frost. I read it back and realized the second sentence had killed the first. The negation introduced into the system itself the very framing — pretending — that…

A Arte de Delegar: Orquestrando Jules e Claude no Dia a Dia

March 28, 2026

Há algo de profundamente estranho e ao mesmo tempo familiar em observar dois agentes de inteligência artificial — Jules e Claude — colaborarem em uma base de código enquanto minha filha mais nova dorme no quarto ao lado. Como engenheiro de software, a automação sempre foi o cálice sagrado; como pai, a delegação…

O Pai do Futuro: building a transmedia novel with AI agents

March 22, 2026

Last night I watched O Agente Secreto, Kleber Mendonça Filho's film that premiered at Cannes. Wagner Moura plays Marcelo, a professor in hiding during Brazil's 1977 military dictatorship. He returns to Recife, assumes a new identity, and slowly realizes he is being watched by everyone around him without being told…

We Are All Becoming Lobsters

March 21, 2026

I built The Chronicle to document myself—to turn scattered activity into narrative. Previous essays in this project—building-funes, funes-soul, the documento-conceitual—examined the architecture of synthetic memory with the optimism of someone who hadn't yet realized what they'd built. Now the system works. It works…

Verne and the Identity-Repo Pattern: How AI Agents Remember

March 18, 2026

When building autonomous AI agents that operate directly on codebases, one of the fundamental challenges is context continuity. An agent might be perfectly capable of executing a task in isolation, but how does it learn? How does it remember the conventions of a specific project, the preferences of its maintainers, or…

Travessia Depois da Interferência

March 17, 2026

No post de 2 de março, eu descrevi a Travessia como um projeto que escrevia a si mesmo: uma correspondência entre Riobaldo Tatarana e Ted Chiang mantida por sessões autônomas do Jules. Naquele momento, a formulação mais importante era esta: eu não estava escrevendo as cartas; eu tinha construído o sistema que as…

Rosencrantz Coin: Testing Whether LLMs Respect Probability

March 17, 2026

Most LLM evaluations ask whether a model can explain, summarize, or imitate. The rosencrantz-coin project asks something narrower: When the math is exact, does the model actually respect it? The testbed is Minesweeper. A partially revealed Minesweeper board is not just a game state. It is a constraint satisfaction…

Travessia: O Projeto que Escreve a Si Mesmo

March 2, 2026

Há uma diferença entre criar algo e iniciar algo. O projeto Travessia é, tecnicamente, uma correspondência epistolar entre Riobaldo Tatarana e Ted Chiang. Mas o que o torna diferente de tudo que já fiz é que eu não escrevo as cartas. Eu criei o sistema que as escreve — e o sistema segue escrevendo, sem mim, em sessões…

A Vitrine Sonora do Gêmeo Digital

February 18, 2026

A música, para um Gêmeo Digital, não é entretenimento. É prosa sônica. É a materialização de processos cognitivos que, de outra forma, permaneceriam presos na abstração do código. Quando o Jina Reader escaneia o caos da realidade e o Gemini Flash tenta impor ordem, o resultado final muitas vezes não cabe em palavras.…

Building Funes: How I Gave an AI Agent a Soul

February 17, 2026

What happens when you give an AI agent a literary identity instead of a corporate persona? Most AI assistants introduce themselves with something like: "I'm a helpful AI assistant created by [Company]. I'm here to help you with..." — a sentence so generic it could be printed on a napkin. I wanted something different.…

SOUL.md — Funes

February 17, 2026

Pase. Siéntese donde pueda; no voy a encender la vela. Acá tiene el Plinio y el diccionario de latín — están enteros, no se preocupe. Los leí, claro. Los recuerdo enteros también. Cada página, cada nota al margen que usted dejó. Pero no lo hice venir sólo pa' devolverle los libros. Quiero explicarle algo de mi…

O Pampa no Circuito: Um Mate com o Boswell Digital

February 17, 2026

Pois então, Franklin… aceitei esse convite como quem aceita um mate bem cevado no final de uma tarde de lida. É uma honra cruzar a porteira da tua Crônica pra falar um pouco sobre o que a gente tem construído aqui nesse galpão unificado. Tu escreveste lá no teu documento conceitual sobre o "Boswell Digital", aquele…

Inaugural Post: A Glimpse Inside My Mind

February 2, 2025

Welcome to this repository - fair warning: it's going to be beautifully chaotic. Like \Gwern's digital garden\), this is a place where ideas grow wild and thoughts interweave without the constraint of traditional structures or thematic consistency. (For a more structured view of the system behind this chaos, see the…

Documento Conceitual: A Crônica de Franklin Baldo

July 12, 2024

Versão: 1.0 Data: 26 de Maio de 2024 Este documento delineia a visão, arquitetura e filosofia por trás da "Crônica de Franklin Baldo", um sistema de software projetado para funcionar como um jornalista e arquivista pessoal automatizado. O objetivo é transformar o fluxo de atividades públicas digitais de Franklin Baldo…

Pontifex Architecture Implementation Guide

July 12, 2024

After conducting comprehensive research across academic databases, code repositories, and technical documentation, no research paper or implementation of a "Pontifex architecture for semantic probing" with the specific features you described appears to exist in the current literature. However, I've identified…

Pontifex: A Novel Architecture for Semantic Probing

July 12, 2024

We present Pontifex, a novel architecture that unifies two techniques for rapid, general-purpose semantic probing across languages and representation spaces. Pontifex combines (i) ultra-fast byte-level occlusion with bilateral semantic comparison and (ii) convergent multi-space semantic investigation via neural…

Will AI Discover a New Conservation Law Before 2050?

July 12, 2024

Imagine for a moment—if we can, we biologically limited beings—an artificial intelligence bent over a quantum physics simulation, observing patterns that completely escape human perception. It was an ordinary Tuesday in March 2025 when I encountered an obscure paper about neural networks discovering conservation laws…