Greptile expands bug detection beyond traditional code review by leveraging GPT-6 Astra to test user workflows, employing Daybreak to enhance security, and utilizing Codex to cut down on rework. This multi‑tool approach allows the platform to identify issues across different stages of development and deployment. By integrating these AI models, Greptile aims to streamline the testing process and improve overall software quality.
CodeRabbit employs GPT‑6.1 Sol to scan and identify security risks within complex codebases. The platform’s security agent assists developers by reviewing the findings and suggesting potential fixes. This integration aims to streamline the process of detecting and addressing vulnerabilities in large code projects.
The paper investigates whether reviewers with limited expertise can reliably determine if a coding agent’s patch resolves a bug, using 411 execution-labeled traces from three agents and 101 controlled cases. It finds that providing structured but unchecked evidence can improve defect detection and reduce over-rejection, and that a frozen cascade of static errors and generated tests achieves high coverage and catch rates on held‑out GPT‑5.4 and Gemini traces. Reviewer size alone does not predict quality, and the study highlights the challenge of creating reliable checks without official tests.
The paper introduces SecPRBench, a benchmark that evaluates large language model agents on real-world bug‑introducing commits from critical software systems such as Firefox, V8, and OpenSSL. It automates harvesting, building, and validating these commits, and uses an LLM‑as‑a‑judge to match findings with ground‑truth vulnerabilities. Across eight state‑of‑the‑art models, recall ranges from 32.5% to 78.1%, with Grok 4.6 and GPT‑6 sol performing best, while security‑focused harnesses like OpenAI’s Codex Security and Anthropic’s Defending Code influence recall differently.
How Braintrust engineers use Codex with GPT-5. 5 to run experiments and code faster.
arXiv:2601.19066v3 Announce Type: replace-cross Abstract: Bug Reproduction Tests (BRTs) have been used in many Automated Program Repair (APR) systems, primarily for validating fixes and aiding fix ge...
Legora employed GPT‑6 Astra to review 41 documents in just minutes, successfully identifying all four planted errors. The use of the model also led to a nearly 40% improvement in performance within this financial‑review workflow.
Perplexity trusts GPT‑6 Astra to handle end‑to‑end systems, using it to write communications, modify software, and monitor production systems. The company reports that it now checks in much less frequently than with earlier models.
CyberDual is a competitive framework where AI agents act as both attackers and reviewers in real software maintenance tasks. Attackers embed exploitable bugs into open‑source projects, while reviewer agents attempt to detect and fix them; success is measured by re‑executing the attacker’s proof‑of‑concept on the reviewed code. Across 1,088 valid attacks, three reviewers caught 85‑91% of bugs, yet about one in six attacks still produced a working exploit after review, highlighting gaps in current AI code‑review tools.
See how a group of leading developers use GPT-5 for the first time.
arXiv:2607. 00990v1 Announce Type: cross Abstract: Large language model (LLM)-based software engineering agents are increasingly developed to resolve software issues by generating patches from issue reports and code repositories.
GPT-5. 1 is now available in the API, bringing faster adaptive reasoning, extended prompt caching, improved coding performance, and new apply_patch and shell tools.
How engineers at Nextdoor use Codex with GPT-5. 5 to investigate hard-to-reproduce issues, build across platforms, and focus on product outcomes.