Compile real-world Claude Code and Codex trajectories into verified, tradable post-training assets.

Procedural data generators for verifiable reasoning, synthetic pretraining, post-training, evaluation, and RL.

Context & Guide For Reinforcement Learning with Verifiable Rewards with Large Language Models

Score the trustworthiness of outputs from any LLM in real-time

A curated list of rubrics, checklists, criteria sets, principles, and scoring guides used to score, rank, verify, filter, or train modern generative models.

Open Arena: SLM verifiers across observability platforms, dataset and model catalogs, and value scenarios for LLM, agentic and harness evals.

Write loops, not prompts. The loop is easy — the verifier is the whole game. VCN night one at Network School.

An RL Enviorment for AES Inversion

A verifiers RLM environment for testing whether adaptive recursive search outperforms brittle manual RAG choreography on long synthetic corpora.

Adversarial QA for LLM-RL environments: find out what reward an empty answer earns. Model-free, zero API cost.

An open reinforcement-learning (RL) environment that trains LLM agents to use the current fact, not the stale one — verifiable reward for temporal fact-currency, built on verifiers / prime-rl (GRPO, LoRA).

Reproducible verifier audits, datasheets, agreement metrics, and release gates

Typed asset shapes + visual + headless views for AI agents. One asset definition. Three rendering targets (HTML / Markdown / Text).

Deterministic three.js frontier game and Prime Intellect Verifiers v1 agent environment

A verifiers RL environment that trains models to propose novel, evidence-grounded, falsifiable hypotheses. Rewards novelty with accountability.

Verifiers hello world repo

Single-turn calendar arithmetic RL environment for Prime Intellect: datetime gold solver, exact+format+partial grader, vf-eval ready.

A verifiable RL environment for TRP ion-channel ligand pharmacology, built on Prime Intellect's Verifiers

Running, reproducing, and testing AI agent environments to understand how they work.

Research proposal for verifier-gated on-policy distillation with explicit evaluation and claim boundaries