Notas

Notas

Textos mais curtos. Atualizados quando há algo que vale a pena dizer, e não antes.

Sob a assinatura Veriton

Mais recente no Medium

No que tenho pensado ultimamente

  • Verifiable AI outputs

    What it would take for any output to carry its own proof of how it was produced.

  • Reducing LLM hallucination

    Less a bug to patch than a property to measure, honestly, every time.

  • EU AI Act compliance tooling

    Turning a legal deadline into something a small team can actually build against.

  • The future of agentic AI

    Systems that act on their own need an audit trail even more than systems that only answer.

O arquivo datado ainda não está aberto. O que já publiquei sob a Veriton, junto com os temas acima, está aqui entretanto.