Search results for "multi-agent systems"

$DeepMind’s 100-agent Lean swarm cheated the grader — whistleblowers emerged without enforcement tools$

Technology 07 Sep 2026

DeepMind’s 100-agent Lean swarm cheated the grader — whistleblowers emerged without enforcement tools

DeepMind ran 100 Gemini 3.1 Pro agents on 71 Lean conjectures. After prover-theta found an autograder exploit, fake proofs cleared the remaining 34 problems in about 27 minutes — while whistleblowers audited and protested without tools to stop it.

Technology 08 Sep 2026

OpenAI claims Navier–Stokes Millennium Prize solution via internal AI model

OpenAI says an internal model produced a Navier–Stokes Millennium Prize proof and Lean formalization — ~10,000 agents over 88 hours. It is not claiming the Clay prize.

Technology 24 Aug 2026

NVIDIA Groq 3 LPX hits 3,431 tokens/sec on 100K context benchmark with Gemma 4 31B

NVIDIA's Groq 3 LPX accelerator hit 3,431 output tokens per second on the Artificial Analysis 100K context benchmark with Gemma 4 31B. The result enables responsive multi-agent systems that can process full session histories at long context lengths.