AI 导读
本地模型可升级为前沿顾问。由用户门控,标记 PII,仅提供文本指导。 在 Terminal Bench 2.1 上,升级将得分从 59.6% 提升至 73.0%,每次 rollout 成本 $0.415,以三分之二的成本弥补了约五分之三的前沿差距。https://t.co/7JnORP4xmZ
正文
The local model can escalate to frontier advisor. It's user-gated, PII-flagged, text guidance only.
On Terminal Bench 2.1, escalation lifts the score from 59.6% to 73.0% at $0.415 per rollout, recovering about three-fifths of the frontier gap at two-thirds of the cost. https://t.co/7JnORP4xmZ
来源:@perplexity_ai · x.com