GAVEL: When AI Safety Grows a Rulebook
A mechanism-first reading of GAVEL, a rule-based activation monitoring framework that turns model-internal signals into auditable AI governance logic.
A mechanism-first reading of GAVEL, a rule-based activation monitoring framework that turns model-internal signals into auditable AI governance logic.
A mechanism-first reading of an AI molecular-glue pipeline for targeting amyloid-β42, and why its business value is disciplined triage rather than instant drug discovery.
Health-SCORE shows how reusable, adaptive rubrics can turn expert medical judgment into a scalable control layer for healthcare LLMs.
A mechanism-first reading of CASTER, a context-aware router that cuts multi-agent LLM costs by deciding when expensive reasoning is actually needed.
A mechanism-first reading of why visual generation helps reasoning only when the task needs a visual world model, not whenever a model can draw.
A practical reading of memorization-heavy evaluation: why models that remember too well can still be risky, and why controllable forgetting may need to be designed into training itself.
FadeMem shows why scalable AI agent memory may depend less on storing everything and more on governing what should fade, merge, or survive.
A sharper look at why the strategyr refactor matters: not because it adds more indicators, but because it clarifies where market description ends and trading intent begins.
A mechanism-first reading of TEA-Bench, showing why tool-augmented emotional support agents need grounded context, selective tool use, and careful evaluation—not just warmer wording.
A mechanism-first reading of MemCtrl, a lightweight memory-control method that teaches small embodied AI agents to filter observations before they flood context.