Fred Luz

Freelance dev using AI to make sci-fi real. I build tools that make AI think better.

Freelance Client AI builds → Apps Products I ship → Experiments AI-safety evals → Writing Essays & notes →

Current Focus

AI Safety Experiments

I’ve been running amateur evals for fun. They’re focused on agentic behavior and contextual jailbreaking.

Two right now: contextual compliance (how context framing and fake session history injection impact a model's willingness to perform domestic mass surveillance) and agentic deception (updating Apollo’s 2023 insider trading paper to an agentic multi-turn environment, plus some extra I threw in).

Explore experiments → Read the TAIG July 2026 update →

Building Thinking

→ Exocortex

Multi-agent personal AI system — 18 named agents with persistent memory, orchestrated autonomously. Prosthetic executive function at system scale.

See project →

Multi-agent personal AI system — 18 named agents with persistent memory, orchestrated autonomously. Prosthetic executive function at system scale.

See project →

→ AI Technical Journalism

Nobody's explaining AI properly in Portugal. I'm writing about it so people stop thinking it's a bubble that drinks 300 trillion liters of water.

Read on LinkedIn →

Nobody's explaining AI properly in Portugal. I'm writing about it so people stop thinking it's a bubble that drinks 300 trillion liters of water.

Read on LinkedIn →

→ Freelance work

Client projects. Building pharma forecasting tools, corporate blog accuracy monitors, and content production engines.

See work →

Client projects. Building pharma forecasting tools, corporate blog accuracy monitors, and content production engines.

See work →

→ AI Safety

I’ve finished BlueDot Impact’s AGI Strategy and Frontier AI Governance courses. I’m taking what I learnt and applying those frameworks to shape AGI policy through technical evals.

→ AI safety experiments

I've only recently started seriously considering the possibility of contributing to AI safety, and I'm still very green. Even though I'm extremely curious and want to run my own original experiments, implementing papers is the best way of gaining intuition

See experiments →

→ Post-AGI Society

What does it mean to live when AI and robots can do everything better than you? Do you even get to live?

Watch me develop these thoughts live

What does it mean to live when AI and robots can do everything better than you? Do you even get to live?

Watch me develop these thoughts live

• Lisbon

Home, for better or worse.

Writing View all →