Shashwat Goel(@ShashwatGoel7):Did you know you can run multi-agent experiments in FutureSim? Among many interesting behaviours, deepseek agents start updating towards the aggregate prediction on each Q, which is observable to them. Many fascinating things to explore here, like agent created+resolved qs 👾

2026.05.17 16:02

Did you know you can run multi-agent experiments in FutureSim? Among many interesting behaviours, deepseek agents start updating towards the aggregate prediction on each Q, which is observable to them. Many fascinating things to explore here, like agent created+resolved qs 👾

Shashwat Goel@ShashwatGoel7

2026.05.15 17:14

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.