ZEN INVESTING
zen investing
OpenAI Abandons SWE-bench Verified After Finding 59% of Failed Tests Were Flawed
OpenAI reveals major contamination issues in SWE-bench Verified benchmark, showing frontier AI models memorized solutions and tests rejected correct code.
zen investing
Together AI Drops Largest Open Dataset for Training Coding Agents
TogetherCoder-Preview releases 161K verified coding trajectories achieving 59.4% on SWE-Bench, giving developers unprecedented training data for AI agents.