OpenEnv

Modern Post-Training: A Deep Dive — Will Brown, Prime Intellect

Jul 13, 2026 · 46:52

Will Brown of Prime Intellect details the company's open-source ecosystem of post-training tools, including the verifiers and prime-rl libraries, arguing they enable efficient and affordable training of frontier agentic models for enterprises. Verifiers V1 decomposes environments into tasks, harnesses, and runtimes using a decorator pattern and Pydantic, supporting group rewards like conciseness bonuses. Prime-RL is an asynchronous reinforcement learning framework that allows long-horizon coding rollouts to overlap, achieving a GLM-5 step on 28 nodes in under 5 minutes for 131k context, with a 1,000-step run costing roughly $50k. The framework supports custom algorithms including on-policy distillation, GRPO, and self-distillation via decomposable loss and algorithm classes. Prime Intellect's Lab platform offers hosted multi-tenant LoRA training live now, with full fine-tuning arriving soon, enabling enterprises to develop environments on CPU and push them to the cloud for scalable post-training.

Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel

Jun 10, 2026 · 20:56

Kobie Crawford of Snorkel explains how a 4B parameter model fine-tuned via RL for under $500 outperformed Qwen 3 235B on financial analysis tool use. The key was training tool discipline—inspecting schemas and self-correcting errors—not deeper reasoning. Single-table training alone boosted multi-table FinQA benchmark from 13.9% to 26.6%, and breaking evals into rubrics identifies which behaviors to fix.

Task Fidelity Scaling Laws — Kobie Crawdord, Snorkel

Jun 2, 2026 · 20:40

Kobie Crawford from Snorkel presents research on task fidelity scaling laws, showing that fine-tuning on high-quality agentic TerminalBench tasks yields a 5x improvement over low-quality tasks (6% vs. 1% uplift) with the same model, compute, and task count. Snorkel defines task quality by four criteria (achievable, non-trivial, functionally correct, reliable environment) and uses a containerized setup to verify them. Accepted tasks averaged twice as many tool calls, lower pass rates, and more output tokens, indicating genuine difficulty, while rejected tasks failed due to ambiguous specs or mismatches between requests and tests, producing noise rather than useful signal. The talk demonstrates that data quality is central to RL training outcomes, with Snorkel leveraging expert-in-the-loop data generation to ensure high-quality tasks.