Overview: LLMs help developers identify and fix complex code issues faster by automatically understanding the full project ...

Apiiro closed 2025 with 104% ARR growth, a reflection of the increased demand from enterprises seeking to manage the risks ...

Abstract: In this paper, we propose a novel classification method that utilizes syntax trees and perplexity to identify jailbreak attacks that use hostile suffixes to make large language models (LLMs) ...

As large language models (LLMs) continue to improve at writing code, a key challenge has emerged: enabling them to generate complex, high-quality training data that actually reflects real-world ...

In the fast-evolving world of AI-generated code, reviewing that code has become the new bottleneck. CodeAnt AI, a San Francisco-based startup backed by Y Combinator, has just raised $2 million in seed ...

We already have the ability to view the syntax tree of a file with the viewSyntaxTree command. This renders the tree for a snapshot of the file. It would be nice if we can also view the syntax tree ...

Sonar’s acquisition of AutoCodeRover, announced on February 19, 2025, marks a strategic move to integrate agentic AI into enterprise software development. The deal positions the Geneva-based code ...

Abstract: Autoencoder models of source code are an emerging alternative to autoregressive large language models with important benefits for genetic improvement of software. We hypothesize that encoder ...

The tech giant has developed a step-by-step AI toolkit that it says has improved end-to-end code migrations by 50%. Code migration is a critical process in maintaining software applications. It helps ...