Effective Altruism Forum
EA Forum

Samuel Pedrielli

Independent Researcher @ Independent Researcher

1 karmaJoined Jul 2025Working (15+ years)

Posts
3

Sorted by New

2

RLHF might be aligning the wrong thing. A different approach.

Samuel Pedrielli

· 2d ago · 6m read

1

Ego-Centric Architecture for AGI Safety v2: Technical Core, Falsifiable Predictions, and a Minimal Experiment

Samuel Pedrielli

· 4mo ago · 7m read

1

Ego‑Centric Architecture for AGI Safety: Technical Core, Falsifiable Predictions, and a Minimal Experiment

Samuel Pedrielli

· 4mo ago · 3m read

Comments
1

Ego‑Centric Architecture for AGI Safety: Technical Core, Falsifiable Predictions, and a Minimal Experiment

Samuel Pedrielli4mo1

0

0

Thanks for reading — I welcome technical feedback on the three falsifiable predictions and the minimal experiment design. I’ll respond within 24–48h.