The AI safety check that runs on a laptop and nearly matched a 35B model

T2Covered by 1 source · first reported by The New Stack at 05 Oct, 18:36 UTC

Guardrail selection has typically meant choosing between a purpose-built classifier and an LLM acting as a judge. Decision models such The post The AI safety check that runs on a laptop and nearly matched a 35B model appeared first on The New Stack.

aidev

Sources

• T2The AI safety check that runs on a laptop and nearly matched a 35B modelThe New Stack05 Oct, 18:36