Solving the Wrong Problem Works Better - Robert Lange

Stepping stones precede breakthroughs

Innovation follows an evolutionary tree where diverse intermediate discoveries must be collected before converging on solutions, rather than through direct optimization toward fixed goals.

Problem invention enables solutions

True creativity often requires inventing new problems recursively before solving them, a capability current AI systems lack when restricted to static, human-defined evaluation functions.

Adaptive multi-model ensembling

The system dynamically selects between frontier LLMs including GPT and Gemini based on which model best suits specific program parents, significantly improving sample efficiency over single-model approaches.

Island populations with knowledge diffusion

Programs evolve in parallel islands with an archive database that diffuses successful mutations across populations, using LLMs to edit or cross-over code based on real-time evaluator feedback.

Self-adaptive evolution

The evolutionary algorithm co-evolves its own parameters during runtime, continuously adjusting model prioritization strategies as the optimization progresses.

Novelty stagnation in autonomous mode

LLMs running autonomously quickly plateau without generating interesting discoveries, remaining parasitic on their starting conditions and unable to escape local optima without human intervention.

Starting point sensitivity

Systems beginning with highly optimized solutions get trapped in local optima, while impoverished starting points enable greater diversity but require significantly longer optimization horizons.

Verification bottlenecks

Generating candidate solutions is computationally cheaper than hard-verifying correctness, creating fundamental bottlenecks for autonomous scientific discovery systems.