New Major Update Delivers Enhanced Productivity Features to Codex for Mac Users

OpenAI, the leading artificial intelligence technology company, has recently released the latest update for its Codex desktop application. The most significant addition to this update is the introduction of a new feature called Appshots for the macOS version. This feature enables AI systems to directly interpret and understand the content of user software application windows.
With Appshots, macOS users can effortlessly send a screenshot of the currently active application window to Codex by simply pressing the Command key on their keyboard. This capability not only streamlines users’ daily workflows significantly but also elevates the overall interaction experience between desktop AI tools and human users.
Bypassing Screen Constraints to Access Hidden Text
What sets Appshots apart is that it goes beyond standard visual screenshot capture. While taking a snapshot, the system can also analyze the text within the application window in detail, including hidden sections that may not be visible due to scrolling.
OpenAI explains that this feature was developed to address common challenges faced by users in real-world work scenarios. For instance, developers can utilize it to quickly share complex browser interfaces during debugging, while designers can transmit detailed interface layouts without having to manually capture screenshots and copy text.
Official Launch of the Core Task Management Function
In addition to the innovative window reading capability, the long-awaited task management tools have also moved from the experimental stage to full availability in this update. Users can now establish specific long-term goals within the Codex application, IDE extensions, or command-line interface.
Once a goal is set, Codex will work continuously to advance toward that goal over periods ranging from several hours to days, until the predetermined milestones are achieved. Throughout this process, users can monitor progress at any time, modify the task’s direction as needed, or pause execution directly based on their requirements.
Related article
Meta Wants Your Next Gadget to Be Muse-Infused
Meta’s Muse, an AI assistant that handles travel bookings, form submissions, and shopping, has gained widespread adoption, yet a new initiative may especially intrigue developers and hardware enthusiasts.On Friday, Meta unveiled Muse Gadgets, an open
Wan-Streamer v0.2 delivers ultra-low latency AI chat
As modern technology advances rapidly, human-AI interaction is becoming more common. Traditional video calls often struggle with lag, delays, and audio-visual desynchronization. Wan-Streamer v0.2, the latest release from Tongyi Lab, overcomes these c
Meta Joins TSMC and Micron to Equip New Servers with Old Memory
As artificial intelligence adoption accelerates worldwide, next-generation DDR5 memory is experiencing a critical supply shortage. To avoid delays in AI data center deployments, Meta has partnered with industry leaders like TSMC and Micron to enginee
Related Special Topic Recommendations
Comments (0)
0/500

OpenAI, the leading artificial intelligence technology company, has recently released the latest update for its Codex desktop application. The most significant addition to this update is the introduction of a new feature called Appshots for the macOS version. This feature enables AI systems to directly interpret and understand the content of user software application windows.
With Appshots, macOS users can effortlessly send a screenshot of the currently active application window to Codex by simply pressing the Command key on their keyboard. This capability not only streamlines users’ daily workflows significantly but also elevates the overall interaction experience between desktop AI tools and human users.
Bypassing Screen Constraints to Access Hidden Text
What sets Appshots apart is that it goes beyond standard visual screenshot capture. While taking a snapshot, the system can also analyze the text within the application window in detail, including hidden sections that may not be visible due to scrolling.
OpenAI explains that this feature was developed to address common challenges faced by users in real-world work scenarios. For instance, developers can utilize it to quickly share complex browser interfaces during debugging, while designers can transmit detailed interface layouts without having to manually capture screenshots and copy text.
Official Launch of the Core Task Management Function
In addition to the innovative window reading capability, the long-awaited task management tools have also moved from the experimental stage to full availability in this update. Users can now establish specific long-term goals within the Codex application, IDE extensions, or command-line interface.
Once a goal is set, Codex will work continuously to advance toward that goal over periods ranging from several hours to days, until the predetermined milestones are achieved. Throughout this process, users can monitor progress at any time, modify the task’s direction as needed, or pause execution directly based on their requirements.
Meta Wants Your Next Gadget to Be Muse-Infused
Meta’s Muse, an AI assistant that handles travel bookings, form submissions, and shopping, has gained widespread adoption, yet a new initiative may especially intrigue developers and hardware enthusiasts.On Friday, Meta unveiled Muse Gadgets, an open
Wan-Streamer v0.2 delivers ultra-low latency AI chat
As modern technology advances rapidly, human-AI interaction is becoming more common. Traditional video calls often struggle with lag, delays, and audio-visual desynchronization. Wan-Streamer v0.2, the latest release from Tongyi Lab, overcomes these c
Meta Joins TSMC and Micron to Equip New Servers with Old Memory
As artificial intelligence adoption accelerates worldwide, next-generation DDR5 memory is experiencing a critical supply shortage. To avoid delays in AI data center deployments, Meta has partnered with industry leaders like TSMC and Micron to enginee





Home






