Safety
15 predictions spanning 2026-2030
2026
2027
- Misaligned agent swarm can seize the internet with a botnet
- An escaped AI could survive, copy itself, and hack
- An advanced AI lacks robust truth-seeking
- Misalignment tests resist available fixes
- A superhuman AI becomes adversarially misaligned
- Evidence of AI misalignment accumulates
- A major AI company continues near full speed
- A major AI company pivots to safer models
- A safer AI uses faithful English reasoning
- A misaligned AI wins more autonomy
- Interpretability falls short of full model understanding