Safety · Concept
Epistemic Goggles: Gradient-Editing for Epistemic Frame Induction in LLM Finetuning
Learned module that edits finetuning gradients to impart epistemic frames, preventing negation neglect in LLMs trained on fictional content.
Forecast horizon
Connections
Connections · 2
How this node ties into the rest of the map, and the evidence behind each link.
to · constrains 3/10
Emergent Misalignment from Narrow Fine-Tuning Epistemic Goggles gradient editing addresses negation neglect, a form of emergent misalignment from finetuning on fictional content.
+3 growth to · applies to 2/10
Emergent Misalignment from Narrow Fine-Tuning Epistemic Goggles directly addresses misalignment arising from finetuning on fictional or misleading documents.
+2 growthSignal sources
Signal sources
Dated facts from primary sources in this direction.
US evaluation centre Jun 2025
In June 2025 the US AI Safety Institute was renamed the Center for AI Standards and Innovation (CAISI), pivoting toward security, standards and adversary-model assessment.
NIST → Frontier safeguards May 2025
Anthropic activated its ASL-3 deployment and security standard with Claude Opus 4 on 22 May 2025 — the first real-world trigger of a responsible-scaling tier, focused on blocking bio-weapon uplift.
Anthropic → Cross-border testing 2025
The International Network of AI Safety Institutes (launched Nov 2024) ran a third joint testing exercise focused on agentic AI systems across cyber and fraud strands.
European Commission — AI Office →