Tracking AI existential risk. Auto-aggregated headlines. Human-curated analysis.
AGGREGATING 47 SOURCES · UPDATED LIVE
Analysis

Extracting Performant Algorithms Using Mechanistic Interpretability

Zac Boring March 14, 2026 1 min read
Read original source →

A Prequel: The Tree of Life Inside a DNA Language ModelLast year, researchers at Goodfire AI took Evo 2, a genomic foundation model, and found, quite literally, the evolutionary tree of life inside. The phylogenetic relationships between thousands of species were encoded as a curved manifold in the model's internal activations, with geodesic distances along that manifold tracking actual evolutionary branch lengths. Bacteria that diverged hundreds of millions of years ago were far apart on the ma

By Ihor Kendiukhov

Read the full article at LessWrong AI →