Even if sloppy empirical patchwork suffices, rigorous alignment research is still worth trying

geoffreyirving · x · 2026-09-04

Geoffrey Irving opens his thread noting we may have no time for anything but sloppy empirical patchwork — written the same day OpenAI announced another agent swarm — and that the patchwork might even be enough. Still, he argues, rigorous agent foundations research is worth pursuing, for reasons he elaborates in the thread.

Related event: Irving Explains Why Rigorous Alignment Research Remains Worthwhile(2 posts)→

Original post →

More from Safety

Safety channel →