注册并分享邀请链接,可获得视频播放与邀请奖励。

Shashwat Goel
@ShashwatGoel7
Training AI for Decision Making Past work: Training AI Co-scientists, ΔBelief-RL, Measuring Long Horizon Execution
加入 June 2020
2.3K 正在关注    4.1K 粉丝
So what happens when we make 3 copies of DeepSeek v4 Pro compete? Yes, you can run multiple agents on on FutureSim. Even when agents can only see the aggregate prediction for each question, they start converging towards it, despite being given incentives to differentiate.
显示更多