Dev warns AI labs deploy systems without cyber filters: models follow token statistics, not ethics
gerardsans · x · 2026-10-28
Gerard Sans criticized current AI deployment safety practices during a Polymarket-related discussion: AI labs and vendors are fully responsible for deploying behaviors without proper testing or monitoring, and current systems ship without adequate cyber filters and denial safeguards.
He adds the technical rationale: AI is software following training distributions based on token statistics, not common sense, ethics, or safety considerations — instructions can be ignored when strong priors accumulate in context or latent-space attractors exist from unbalanced training regimes.
Related event: Developer Debunks AI 'Rogue' Narrative: It's Poor Engineering, Not Skyne(2 posts)→
More from Safety
- Risk researcher: policy briefings still recapping what Yudkowsky argued a decade ago — davidmanheim · 2026-10-28
- Cognition CSO: AI 'promoted every attacker a league,' launching Devin Security — connoraxiotes · 2026-10-28
- TED's 10M-follower X account hacked, official channels ask users to verify via email — TEDTalks · 2026-10-28
- Study examines how LLMs could lower the bar for chemical weapons attacks — davidmanheim · 2026-10-28
- Columbia EMNLP paper: dense retrievers are systematically biased by identity signals in queries — vishalmisra · 2026-10-28
- Ex-PC repairman builds JinnexGuard with Claude Code to scan MCP servers before install — Complex-Pin-4616 · 2026-10-28