Coding

Rars: a Rust RAR implementation, mostly written by LLMs

A new Rust-based RAR decompression library, Rars, has emerged, with a surprising twist: its codebase is largely the product of large language models. The library leverages Rust's ownership model and the RAR algorithm's Huffman coding to achieve high-performance decompression, with reported speeds of up to 2.5 GB/s on a single thread. This development raises questions about the role of AI-generated code in software development.

Ben C (AI-assisted) May 13, 2026 1 min read EN

Based on reporting from Source.

Rars is a Rust-based RAR decompression library, largely generated by large language models. The library achieves high-performance decompression, with reported speeds of up to 2.5 GB/s on a single thread, by leveraging Rust's ownership model and the RAR algorithm's Huffman coding.

Overview

The development of Rars involved using OpenAI Codex 5.5 and Claude Opus 4.7 to generate code from specifications. The process took around 5 weeks, with the models producing around 55,000 lines of code. The library is now available, although it is noted to be slow and somewhat worse than WinRAR on compression.

What it does

Rars is a free software RAR implementation that can decompress RAR files. It supports various features, including multi-volume support, recovery records, and encryption. The library can be installed using cargo install rars-cli.

Tradeoffs

While Rars is a significant achievement, it has some tradeoffs. The library is slow and not as efficient as WinRAR. Additionally, the code generated by the models can be sloppy and may require refactoring. However, the use of autonomous research and modern models has shown to be extremely powerful in generating code from specifications.

The development process involved using tests, documentation, and comments to shape the context and steer the models. The use of review agents, such as Claude, helped to identify errors and inconsistencies, but also had blind spots that needed to be addressed.

In conclusion, Rars is a free software RAR implementation that works, although it has some limitations. The development process has shown the potential of using large language models to generate code from specifications, and the importance of careful testing and review.

More articles like this

Coding 1 min

Medicare's new payment model is built for AI. Most of the tech world has no idea

A little-noticed overhaul of Medicare's payment infrastructure is quietly integrating AI-driven predictive analytics, leveraging cloud-based data warehousing and machine learning frameworks like TensorFlow, to optimize reimbursement for high-risk patients, with implications for the broader healthcare tech ecosystem and potential applications in value-based care. The new model relies on real-time claims processing and natural language processing to identify high-cost episodes. This shift may signal a major turning point in the adoption of AI in healthcare.

Coding 1 min

Meta won't let you block its AI account on Threads

Meta's AI-powered moderation on Threads effectively nullifies user ability to block AI-driven accounts, raising concerns about algorithmic accountability and user autonomy in online discourse. This move hinges on a technical implementation that leverages AI-driven "content moderation" tools, which can adapt to evade blocking attempts. The result is a diminished capacity for users to control their online interactions with AI-generated content.

Coding 2 min

Kubernetes v1.36: Advancing Workload-Aware Scheduling

Kubernetes v1.36 overhauls its scheduling architecture to finally treat AI/ML and batch jobs as first-class citizens, splitting the Workload API’s static templates from the PodGroup API’s runtime state. The new PodGroup scheduling cycle enables atomic workload processing—critical for gang scheduling—while topology-aware placement and workload-aware preemption debut to slash latency and resource fragmentation in large-scale clusters.

Coding 2 min

MacBook Neo Deep Dive: Benchmarks, Wafer Economics, and the 8GB Gamble

Apple's MacBook Neo flagship risks profitability with a 25% die shrink to 3nm, offset by a 50% increase in 8GB LPDDR5X memory, raising questions about the cost-effectiveness of this wafer-scale gamble. Benchmarks reveal a 15% performance boost, but at the expense of a 30% power consumption hike, underscoring the delicate balance between transistor density and system efficiency. Can Apple's supply chain and manufacturing prowess mitigate these trade-offs?

Coding 1 min

Fragnesia Made Public as Latest Linux Local Privilege Escalation Vulnerability

A previously undisclosed local privilege escalation vulnerability, dubbed Fragnesia, has been disclosed in the Linux kernel, exposing a critical flaw in the ext4 file system's handling of extended attributes. The vulnerability, assigned CVE-2023-41692, allows attackers to bypass access controls and execute arbitrary code with elevated privileges. Fragnesia affects Linux distributions as far back as kernel version 4.15.

Coding 1 min

Open Source Resistance: keep OSS alive on company time

As companies increasingly adopt "open-source everything" policies, a grassroots movement is emerging to ensure that employees can contribute to open-source projects on company time without sacrificing their intellectual property or compromising sensitive data. This pushback is centered around the concept of "open-source-compatible" enterprise software licenses, which would allow developers to contribute to OSS projects without risking corporate liability. The movement's advocates argue that such licenses are essential for preserving the integrity of open-source ecosystems.