Safety Researchers Say Alignment Lags Far Behind Capabilities

AI safety researchers Marius Hobbhahn and Matthew Burt reaffirm the field's consensus that alignment progress lags far behind capabilities, noting that no one knows how to align superhuman models—or even current ones—a view echoed by lab leadership.

2026-11-11 ~ 2026-11-11 · 4 related posts

• Alignment progress lags far behind capabilities — nobody knows how to align superhuman models — MariusHobbhahn · 2026-11-11
• Nobody knows how to align superhuman models, and safety is far behind capability — MatthewJBar · 2026-11-11
• Marius Hobbhahn: we have a recipe for capability but not for robust safety — MariusHobbhahn · 2026-11-11
• Alignment vs capability: researchers have a recipe for capability but not for robust safety — sandersted · 2026-11-11