Abliterated GLM-5.3 or DS V4.1 Flash plus compute lets motivated individuals do anything, argues viral thread
khademinori · x · 2026-10-23
Repurposing @JordanNanos' thesis: anyone sufficiently motivated with access to an abliterated (guardrail-removed) GLM-5.3 or DS V4.1 Flash 1013 model and enough compute can do whatever they want right now. The framing: big players can "outrun the bear," small ones must "hide from it" — open-weight models with stripped safety layers have dropped capability thresholds to individual level.
More from Safety
- Fortinet discloses multiple critical and high-severity flaws in FortiOS, FortiManager, FortiAnalyzer — cyb3rops · 2026-10-23
- LiteLLM 1.107.0 ships malware that runs on any Python start; pin 1.106.2 and rotate keys — AIFlow_ML · 2026-10-23
- Naval amplifies take: assume 70% of the Internet was already rooted, AI just exposed it — naval · 2026-10-23
- New paper with 25 coauthors examines feasibility of a hardwired pause on frontier AI training — wfithian · 2026-10-23
- Garrison Lovely publishes Obsolete: a trillion-dollar critique of the AI replacement race — GarrisonLovely · 2026-10-23
- Fired OpenAI safety researchers Balesni and Korbak give first interview on Machine Gods podcast — kevinroose · 2026-10-23