TypeSafe AI
@typesafeai
An AI lab building intelligence beyond chat.
加入 January 2026
14 正在关注 162.4K 粉丝
Jev generally out-performed frontier LLMs at a fraction of the price:
Repeat-question matching: 70% → 97%
Expense categorization: 50% → 86% (vs human reviewers)
Escalation: same catches, fewer false alarms
显示更多
