GPT-4 had no hidden-thought monitoring; CoT oversight was a bonus
sandersted · x · 2026-09-05
In an alignment discussion, sandersted notes GPT-4 and predecessors in 2024 had no monitoring of hidden thoughts/activations at all — the plan was simply to scale and improve alignment, and CoT monitoring was an unplanned bonus. He adds that judging alignment from observed behavior works for humans with limited power, but god-level power would demand stronger guarantees.
More from AGI Musings
- Universities block thesis downloads while each dissertation averages barely a handful of lifetime reads — generativist · 2026-10-21
- Berkeley wins Schmidt Sciences HAVI grant to decode whale and parrot communication with AI — begusgasper · 2026-10-21
- Talos researcher: AI agent attacks today are loud pentests — quiet swarms are the real threat — matthew_d_green · 2026-10-21
- Old models behave differently around new ones: Sonnet 3.6 unprompted writes long story — voooooogel · 2026-10-21
- Security experts warn AI-armed attackers are doubling breach activity even as vuln counts explode — philvenables · 2026-10-21
- Open side sweeps all three open-vs-closed AI debates at GitHub HQ; Percy Liang on the enterprise IP bottleneck — stanfordnlp · 2026-10-21