Blogs

OpenAI invited Patched to fine-tune gpt-4o to build the SOTA model for this benchmark. We worked alongside their team to understand how performance can be improved by fine-tuning frontier models.

We compare fine-tuning GPT-4o-mini, Gemini Flash 1.5, and Llama-3.1-8B models using a custom vulnerability fixes dataset, with GPT-4o-mini showing the most significant improvement and setting a new benchmark.

We discuss Mixture of Agents, an inference optimization technique that enhances gpt-4o-mini to outperform gpt-4-turbo at ~1/50th the cost for a variety of software development tasks.

We introduce Patched Round-Trip Correctness (Patched RTC), a novel, unsupervised evaluation technique for Large Language Models used in diverse software development tasks, offering a self-evaluating framework that measures consistency and robustness without human intervention.

Discover how Gartner's latest insights place Patched at the forefront of AI-augmented DevOps, highlighting its potential to transform software development and delivery.

Explore our latest blog post to learn about the recent polyfill.io supply chain attack that has affected over 100,000 websites and how Patchwork, alongside tools like Semgrep, can help you quickly patch your code.