Cognition 是 Devin 背后的公司，Devin 是一名自主软件工程师，被从大型银行到科技原生初创公司等世界各地的企业所使用。随着 Cognition 的工程团队编写更多代码，审查这些工作已成为一项挑战。Cognition 将 GPT‑6 Astra 测试其工作并展示结果的能力视为让代码审查更高效的一种方式。
“Astra 改进的一大要点是它能够测试并证明其工作确实按你预期的方式运行。”
Walden Yan，Cognition 联合创始人
测试软件并展示结果
Cognition 正在其整个产品线中应用 GPT‑6 Astra。“我们一直在用它来改进我们的产品，包括 Devin 这一核心云代理，也包括我们的 CLI 和桌面产品，”Yan 说。
在一个例子中，Devin 使用 Astra 测试 iPhone 游戏 Otter Run，并返回一段游戏在模拟器中运行的录像，以及一份报告，标明哪些检查通过、哪些区域尚未测试。
录像展示了应用程序的行为，而报告记录了测试的范围。工程师可以利用这些输出检查软件如何工作，并了解还有哪些地方需要关注。
Yan 说，Astra 还帮助 Cognition“更快得多”地回复客户。当客户发送一张 bug 的截图时，团队可以将其交给使用 Astra 的 Devin，它会修复问题并返回一张显示结果的截图。
朝着减少人工代码审查的方向努力
Cognition 将借助 GPT‑6 Astra 实现更强测试视为通往更高效审查流程的一条路径。让 Devin 测试其工作并提供结果证据，可能有助于工程师在更少人工检查代码的情况下评估变更。
“我们预计，随着时间的推移，我们必须人工查看的代码会更少，而最终交付的会更多。这是我们在 GPT-6 方面真正感到兴奋的事情之一。”
Walden Yan，Cognition 联合创始人
Cognition is the company behind Devin, an autonomous software engineer used by businesses around the world, from big banks to tech-native startups. As Cognition’s engineering teams write more code, reviewing that work has become a challenge. Cognition sees GPT‑6 Astra’s ability to test its work and show the results as a way to make code review more efficient.
“One of the big pieces that Astra improves on is its ability to test and prove that its work actually functions the way you expect.”
Walden Yan, Co-founder, Cognition
Testing software and showing the results
Cognition is applying GPT‑6 Astra across its product lineup. “We’ve been using it to make improvements across our product, including the core cloud agent that is Devin, but also our CLI and desktop products,” says Yan.
In one example, Devin uses Astra to test Otter Run, an iPhone game, and returns a recording of the game running in a simulator, alongside a report identifying checks that passed and areas left untested.
The recording shows the application’s behavior, while the report documents the scope of the testing. Engineers can use those outputs to inspect how the software works and understand what still needs attention.
Astra is also helping Cognition get back to customers “much quicker,” says Yan. When a customer sends a screenshot of a bug, the team can pass it to Devin using Astra, which fixes the issue and returns a screenshot showing the result.
Working toward less manual code review
Cognition sees stronger testing with GPT‑6 Astra as a path toward a more efficient review process. Having Devin test its work and provide evidence of the results could help engineers evaluate changes with less manual examination of the code.
“We expect over time that we have to manually look at less code and end up shipping more at the end of the day. This is one of the things we’re really excited about when it comes to GPT-6.”
Walden Yan, Co-founder, Cognition
本文内容采集自官方网站，排版和翻译可能与原页面存在差异。
阅读官方全文