Tagged “classifiers”

2 posts.

All Model Architecture19 Training & Alignment22 Inference & Serving18 Agents & Orchestration11 Reasoning & Evaluation26 Safety, Security & Governance7 Platforms & Practice20

Safety, Security & Governance 21 min

The Moderation Tax: How Guardrail Classifiers Trade Latency for Coverage

A guardrail is a classifier sandwich wrapped around your model, and every layer you add buys coverage with latency and false refusals. Here is how the layer actually works, what it costs, and where it breaks.

llm-safety guardrails content-moderation jailbreaks ∑ ◫

Safety, Security & Governance 24 min

You Cannot Have All Three: COMPAS, Calibration and the Impossibility Theorems of Fair Classification

In 2016 ProPublica showed that COMPAS wrongly flagged 44.9% of Black defendants who never reoffended against 23.5% of white ones, and its vendor showed the scores meant the same thing for both groups. Both were right, and a one-l…

fairness-and-bias fairness bias calibration ∑ ◫