TypeSafe AI 推出 Jev：面向生产的 System One 模型
原标题：Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
AI 摘要
TypeSafe AI CEO Diogo Almeida 在 Latent Space 播客中介绍其公司推出的 Jev 模型，该模型采用名为 RLCD（Reinforcement Learning for Calibrated Decisions）的新技术，针对 System One 任务优化校准概率，而非依赖人类反馈（RLHF）或可验证奖励（RLVR）。Diogo 认为当前前沿模型过度依赖自回归聊天微调，导致幻觉、谄媚和拒绝问题，而 Jev 旨在为软件自动化提供可靠、可组合的智能。他还提出“最苦涩的教训”，强调任务与数据比算力更重要，并认为 TypeSafe 更像数据实验室而非模型实验室。
正文节选
Tickets for AIE NYC and applications for the invite-only AIE CODE now open. Join us! We have an unusual relationship with today’s guest: for years since coauthoring the InstructGPT paper, Diogo Almeida had been saying that API-available frontier models have been going down the wrong path, everything from the alignment to refusals to reliability perspectives, that we have dropped every mode other than autoregressive chat-tuned LLMs because of the overwhelming success of ChatGPT. In a launch video