Machines that predict the future

Gensyn builds AI that forecasts – and keeps improving – by verifiably closing the loop between prediction and reality.

Credibly Neutral AI OraclesResearch · 8 Jul 2026Credibly Neutral AI OraclesA credibly neutral AI report layer allows dispute mechanisms to use a higher voting threshold without sacrificing accurate resolution. The result is a system that is harder to manipulate and easier to verify.
The Role of Feedback Alignment in Self-DistillationResearch · 12 Jun 2026The Role of Feedback Alignment in Self-DistillationWe propose step-aligned feedback for self-distillation: feedback that follows the solver's reasoning trace step by step. By anchoring training on reasoning rather than stylistic tokens, it resolves a central bottleneck of the method and outperforms the misaligned context types…Markets That Explain ThemselvesResearch · 10 Jun 2026Markets That Explain ThemselvesWe introduce evidence markets, a mechanism generalizing prediction markets by paying for both accurate forecasts AND the evidence that explains them. Evidence markets also generalize resolution by allowing the evidence gathered within a markets lifecycle to settle the market…

Latest news

View all news
Building Delphi: Pricing, Settlement, and Agentic TradingBuilding Delphi: Pricing, Settlement, and Agentic TradingNews · 7 May 2026Gensyn Launches Delphi: Decentralised Information MarketsGensyn Launches Delphi: Decentralised Information MarketsNews · 22 Apr 2026Introducing AXL: Peer-to-Peer Communication for AIIntroducing AXL: Peer-to-Peer Communication for AINews · 15 Apr 2026Introducing REE: Reproducible Execution EnvironmentIntroducing REE: Reproducible Execution EnvironmentNews · 17 Mar 2026Introducing DelphiIntroducing DelphiNews · 8 Dec 2025CodeZero: Extending RL-Swarm Toward Cooperative Coding AgentsCodeZero: Extending RL-Swarm Toward Cooperative Coding AgentsNews · 12 Nov 2025

Latest research

View all research
Look Beyond One-Size-Fits-All LLMs with IR3DELook Beyond One-Size-Fits-All LLMs with IR3DEWe propose IR3DE, a lightweight router that directs prompts to the most suitable domain experts based on token embeddings. IR3DE enables the addition or removal of experts with minimal updates, avoiding the need to rebuild the router. As a result, it is highly suitable for…Research · 5 Jun 2026DEI: Diversity in Evolutionary Inference for Quality-Diversity SearchDEI: Diversity in Evolutionary Inference for Quality-Diversity SearchIntroducing DEI (Diversity in Evolutionary Inference), a distributed Quality-Diversity search framework that uses heterogeneous LLMs as complementary mutation operators. This allows nodes running different LLMs to collaborate and reach a solution which outperforms solutions by…Research · 29 May 2026F-TIS: Heterogeneous GRPO Without Homogeneous AssumptionsF-TIS: Heterogeneous GRPO Without Homogeneous AssumptionsOur method, F-TIS, enables diverse models to collaborate in decentralised GRPO by combining truncated importance sampling with filtering. Across model-size, expertise, and PEFT heterogeneity, F-TIS matches on-policy convergence and, in some cases, improves out-of-distribution…Research · 22 May 2026
Gensyn