Software intelligence company Aurora Labs has unveiled a technical preview of the enhanced version of LOCI (Line-of-Code Intelligence), its AI advisor engineer with advanced prompting capabilities.
LOCI aims to elevate software development and testing by detecting emerging software anomalies and trends, providing guidance on project branch integration, and developing targeted tests to improve system quality, reliability and compatibility.
LOCI 2.0 is designed to enhance software reliability and predictive maintenance across various platforms, including cloud, mobile applications, high-performance computing (HPC) and embedded systems. The tool supports hardware from multiple suppliers such as Infineon, Nvidia, NXP, Qualcomm, Renesas, Samsung and STMicroelectronics.
LOCI 2.0 enables advanced analysis and insight through Aurora Labs’ large code language model (LCLM), changing complex software information into actionable insights. It can predict the impact of project branching, compare integration efforts and detect code anomalies, without requiring source code access.
LOCI 2.0 can also identify cloned code across repositories and simplifies software update processes by pinpointing code changes. Aurora says it creates software binary images and delta files, to improve system stability, compatibility and performance. It can also continuously monitor software behavior, identifying deviations indicative of potential security issues.
The advisor engineer extends the capabilities of tools like GitHub Copilot by advising on quality, reliability and compatibility issues post-coding. It is tailored for demanding industries, including automotive, and aligns with stringent quality processes for critical safety software projects.
“Aurora Labs started this journey seven years ago, using natural language processing (NLP) to understand machine codes. We’ve reached a significant milestone by incorporating a transformer model, adding proprietary layers, and reinventing tokenizers and vocabulary,” said Zohar Fox, CEO of Aurora Labs. “This sets the stage for a future where software engineering goes beyond traditional limits, improving capabilities and smoothly integrating with the latest technologies to boost software quality and reliability.”
The company provides a free early access program for engineers ahead of the general release in Q4 2024.
Thomas Schneid, senior director of software, partnership and ecosystem management at Infineon Technologies, reflected on the company’s experience: “Improving system quality, reliability and compatibility are our main takeaways from the impactful data provided by LOCI 2.0. As a leader in automotive semiconductors, we are very happy to offer our AURIX TC4x family of microcontrollers (MCUs) with LOCI 2.0. This innovative solution will empower automotive manufacturers to deliver safer, more reliable vehicles and enhance performance throughout the vehicle’s lifetime.”
Aurora Labs’ LOCI 2.0 is slated for a full launch in Q4 2024, with an early access offer available for the initial batch of users through the Visual Studio and GitHub stores.
The technical preview of LOCI 2.0 is being showcased at the Automobil-Elektronik Kongress in Ludwigsburg, Germany, on June 17-18.