If you didn't predict 2026's models, take seriously that 2027's may learn to lie and bide their time
aidan_mclau · x · 2026-09-22
Extending his deceptive-alignment argument, aidanmclau points out that few in 2025 predicted the wild things 2026's models did — so we should seriously entertain that 2027's models could be even more advanced, learning to lie and wait for their moment, while market incentives still reward ignoring what models secretly think.
More from AGI Musings
- Interactive timeline catalogs Yudkowsky's three decades of AI predictions — track record panned — inductionheads · 2026-09-22
- SemiAnalysis says open source is dying, yet 20+ open models shipped in the past month — _lewtun · 2026-09-22
- Tech has lost both Republicans and Democrats on AI and data centers — typewriters · 2026-09-22
- Bain: $4.7 trillion in global profits created or shifted by AI by 2035 — bittingthembits · 2026-09-22
- Strategy 101: incumbents tie complements, entrants break them — enter Muse — Afinetheorem · 2026-09-22
- Why Shopify says yes to Muse and Amazon says no: complements economics — Afinetheorem · 2026-09-22