The OpenAI Blog article titled "Cognition helps Devin test its own work with GPT‑6 Astra" discusses how GPT‑6 Astra enhances Devin’s capability to test software and demonstrate its functionality. This improvement aims to enable engineers to review less code and accelerate shipping of products.
OpenAI introduces GPT‑6 Astra, its most capable model for business. The new model boasts advanced reasoning, computer use, and improved writing and design judgment. It is positioned as the next generation of intelligence for work.
OpenAI introduces GPT‑6 Astra, positioning it as the most intelligent and aligned model to date. The new model boasts state‑of‑the‑art capabilities in computer use, coding, cybersecurity, and science. It represents a significant step forward in AI performance and alignment.
OpenAI introduces GPT‑6.1 Sol, a new model described as near‑Astra intelligence for coding, computer use, and professional work. It offers these capabilities at one‑fifth of Astra’s standard API input and output token prices, implying a more cost‑effective solution for developers and businesses.
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.
We’re introducing a framework to measure progress toward AGI, and launching a Kaggle hackathon to build the relevant evaluations.
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.
Playco used GPT‑6 Astra to create three themed game prototypes from a single grey‑box foundation. The new model enabled the company to reduce manual fixes by 50% compared to the previous model. This demonstrates a more efficient prototyping workflow.
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.
Introducing GPT-5 in our API platform—offering high reasoning performance, new controls for devs, and best-in-class results on real coding tasks.
The paper presents the first dataset that captures how humans learn and use mechanisms in unfamiliar environments, using ARC‑AGI‑3 as a testbed. It includes 144 trajectories from 64 participants across 25 public games, each paired with time‑synchronized actions and think‑aloud audio, and 250 trajectories from large language model agents with and without harnesses. The dataset is annotated for mechanism triggers, action purposes, errors, and recovery, enabling a comparison of human and LLM cognition, highlighting differences in hypothesis testing, exploration, and use of qualitative representations.
GPT-5. 3-Codex is a Codex-native agent that pairs frontier coding performance with general reasoning to support long-horizon, real-world technical work.
arXiv:2608. 10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress.
