Excited to share MultiVer. With no training, we beat fine-tuned SOTA on Python vulnerability detection with specialized retrieval and agent memory. Zero-shot: 82.7% on PyVul surpassing fine-tuned GPT, 91.7% matching OpenAI's internal Aardvark benchmark.
From Twitter
Disclaimer: The content above is only the author's opinion which does not represent any position of Followin, and is not intended as, and shall not be understood or construed as, investment advice from Followin.
Like
Add to Favorites
Comments
Share
Relevant content



