🔬 Science Sep 21, 2026 · Elizabeth Zonarich

One effort to safeguard humanity: AI ‘constitutions’

Harvard Science
Harvard science news
View Channel →
One effort to safeguard humanity: AI ‘constitutions’
Source ↗ 👁 4 💬 0
Science & Tech


One effort to safeguard humanity: AI ‘constitutions’




Neerav Kingsland (left), Jordi Weinstock, Jack Cushman, and Mahzarin Banaji. Photo by Grace DuVal





Max Larkin

Harvard Staff Writer




September 21, 2026


8 min read




Berkman Klein Center heard calls to keep models ‘honest, helpful, harmless.’ It’s a work in progress.






In one formulation, any human constitution is just a set of guardrai

Comments (0)

Sign in to join the discussion

More Like This

Biologists Discover a Cellular Pathway That Helps Colorectal Cancer Spread
SciTechDaily · 5d ago
Cannabis Users More Likely to Commit and Experience Violence, Study Finds
SciTechDaily · 5d ago
A Surprising Brain Signal Could Explain Why Eating Less Protein Extends Lifespan
SciTechDaily · 5d ago
A Few Picoseconds Reveal Superconductivity’s Hidden Breaking Point
SciTechDaily · 5d ago
Mars’ North Polar Ice Is Much Cleaner Than Scientists Thought
SciTechDaily · 5d ago
Scientists Simulated Moons Being Blown Apart – and Found Something Unexpected
SciTechDaily · 5d ago