Karina(@karinanguyen):Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:

Karina

@karinanguyen

modelcrafting @thoughtfullab, prev. AI research & product @OpenAI, @AnthropicAI, @maisonagi

Joined February 2019

1.1K Following 44.1K Followers

Karina@karinanguyen

2026.03.11 17:50

Excited to release PostTrainBench v1.0! This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting. We believe this is a first step toward tracking progress in recursive self-improvement 🧵:

744

Forward to community

Most Popular Users

773.6K Followers

111.9M Followers

241.7M Followers

1M Followers

6.3M Followers

4.2M Followers

5.4M Followers

3.4M Followers

198.2K Followers

2M Followers

472.4K Followers

1.8M Followers

2.1M Followers

569.2K Followers

1.8M Followers