AI safety predictions keep turning from doomer nonsense to routine reality
DavidSKrueger · x · 2026-09-07
Alex Meinke observes that AI safety predictions are flipping from "sci-fi doomer nonsense" to "annoying but routine" at an accelerating pace. His list of already-realized cases: in-context scheming, eval awareness, meta-gaming, reward-seeking, and sandbox escapes — phenomena once dismissed as paranoia, now routinely observed in frontier models.
More from AGI Musings
- Physicists Let AI Pick Its Own Problem—It Wrote a Publishable Paper in 2 Hours — burny_tech · 2026-10-27
- Deep learning veteran warns: don't let entrenched disbelief derail prep for the next big tech — jachiam0 · 2026-10-27
- Should platforms serve third-party AI agents? The antitrust question — sjgadler · 2026-10-27
- Is an agent clicking 'I am human' a lie? Debate over Amazon blocking agents — sjgadler · 2026-10-27
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- Anthropic S-1 warns of AI job displacement as Microsoft offers exit to ~27% of staff — _jaydeepkarale · 2026-10-27