Agents & InferenceTechCrunch

Unreleased Anthropic model tested 650 ideas on the Riemann hypothesis

Which summary reads better? Pick one — models revealed after.Both summaries are AI-generated.

Match the models (Optional)

Which model wrote which summary? Select a matchup mapping below before voting.

Summary A

An unreleased Anthropic model autonomously ran a 1.5-day, 60-subagent orchestration burning 31 million output tokens across 650 candidate approaches, and produced a genuine, Lean-formalized advance on the Riemann hypothesis—directed by a non-mathematician. The signal for you isn't the math result but the operational proof point: long-horizon, self-coordinating multi-agent runs at massive token spend can now generate expert-verified novel output, which means your agent architectures and cost/token budgeting should plan for extended autonomous swarms with dedicated validator agents rather than single-shot calls.

LinkedIn

Two AI summaries of each story, blind-voted — see today's agents & inference digest →