// HACKER NEWS — CYBERSECURITY
GPT-6 Astra in code review: Gains, privacy, and cost
Some of the hardest work in code review happens outside the changed lines. A change can look correct in isolation and still break code elsewhere in the system.
That is what makes our early results for OpenAI's GPT-6 Astra most interesting. In our evaluation, Astra caught approximately 4% more labeled bugs through actionable findings than GPT-5.6 Sol, and 22% more than Opus 5.
The biggest jump comes on harder cross-file reviews, where Astra's gains reach 20% over Sol and 33% over Opus 5. Using that capability at customer scale also means protecting customer data and assessing the model’s public API pricing.
Our measure here is actionable bug coverage, meaning how many labeled bugs a model catches through findings a developer can act on.
The overall gain over GPT-5.6 Sol appears modest in this first evaluation measure. This evaluation also includes simpler reviews, where there may be less room for a stronger model to differentiate itself; Astra's larger advantage appears in the harder cross-file subset. It is an early, directional result.
The harder cross-file comparison is more encouraging. Astra's relative advantage grows to 20% over Sol and 33% over Opus 5. That suggests value in connecting a change's intent to consequences distributed across a codebase.
These results describe one part of review performance. They do not establish an overall ranking of review quality, predict a team's defect rate, or promise the same gain on every pull request.
A large context window creates room for information. Useful reasoning requires the model to identify which pieces matter, connect them, and reach a conclusion supported by evidence.
Our interpretation is that Astra's most interesting advance lies in connecting the right information. Its larger gains on harder cross-file reviews suggest progress on work where relevant information is distributed. They do not isolate the cause of that progress or prove that more context alone improves a model's performance.
OpenAI positions Astra for multistep work across code, browsers, and professional software.