腾讯WorkBuddy上线AI协同编辑，支持Word、Excel和PPT
Related
OpenAI Codex will integrate with the next-generation flagship model GPT-5.6 Sol Ultra.
According to Beating, Thibault Sottiaux, head of core products at OpenAI, confirmed on social media that the Ultra version of the next-generation flagship model, GPT-5.6 Sol, will be integrated into Codex. Previously, some users complained that OpenAI's decision not to include GPT-5.5 Pro in Codex was a major mistake; if GPT-5.6 Ultra were included, developers wouldn't even need to pay for Claude anymore. Sottiaux subsequently confirmed publicly that the Ultra version is indeed in Codex's plans.
The culprit behind the exhausted Codex credit limit has been identified; OpenAI has fixed multiple vulnerabilities and implemented a third round of full-scale compensation resets.
According to Beating's monitoring, the cause of the abnormal consumption of credit limits in Codex, a programming intelligence agent under OpenAI, has been officially identified. Tibo Sottiaux, the core product manager, announced that the team has deployed a patch to fix the issue across all users. In addition to resetting the credit limits for all users, all users will also receive an additional reset card valid for 24 hours. The excessive consumption was not caused by a single vulnerability, but by a combination of multiple minor backend issues and display false alarms. At the operational level, the system's automatic review was too frequent, unexpectedly triggering too many sub-agent tasks, and the backend suggestion function repeatedly ran and retried after failure, consuming tokens exponentially. At the display level, automatic review was incorrectly classified as GPT-5.4 consumption, and failed or rate-limited requests were also incorrectly displayed as credit consumption in the frontend charts, directly causing a credit shortage for all users. Currently, the official team has deployed a hotfix patch simultaneously on the billing backend, desktop client, and CLI terminal. In addition to resetting the credit limits for all users, only successful interaction requests will be recorded in the Turn statistics chart in the future. Although the erroneous data in the historical charts cannot be changed, the actual token consumption after the update will be significantly reduced.
Codex's account balance crashed again, and OpenAI had to perform a full hard reset.
According to Beating's monitoring, the vulnerability in Codex, OpenAI's programming agent, regarding abnormal credit limit consumption remains unresolved. Tibo Sottiaux, the core product lead, announced that the team urgently opened the war room to check logs on Sunday and performed a second hard reset for all users. The initial reset on June 27th failed to resolve the issue. Some users reported that their limits dropped by 75% again just 36 hours after manually resetting their limits. Independent developer nicdunz criticized OpenAI for being too lax in its response to the fault. Sottiaux revealed that because the fault is still under investigation, the team decided to directly refresh all users' credit limits. Given that some users had previously accumulated up to three self-resets of their limits, this time a direct reset was implemented instead of issuing credit limit reset cards. Coincidentally, this week is OpenAI's rest and relaxation week, internally called RESET week. The R&D team, who should have been enjoying a break, ended up spending their holiday in the war room resetting the entire network's credit limits.
OpenAI upgrades Codex experience: Supports hover-to-jump and zoom alignment for long dialogues.
According to Beating's monitoring, Codex released an update this week, resolving issues with inconvenient navigation in long conversations and misalignment of interface elements when scaling. For long conversations, Codex introduced a navigation rail, allowing users to preview and jump directly to the next conversation turn by hovering the cursor over the edge of the slot. Simultaneously, thread scrolling is smoothed, automatically maintaining the browsing position when switching within long conversations. Alignment protection has been added to the interface when scaling, ensuring that elements such as tooltips, menus, dialog boxes, selection bubbles, drag-and-drop previews, and auto-completion do not become misaligned. The search settings have been expanded to include richer appearance controls, host filtering, and custom Provider settings, and a new panel specifically for pets has been added. Archive management has been simplified, and unread badges in the Dock and sidebar have been synchronized. In terms of underlying performance and collaboration, the update reduces the background workload of thread switching and supports segmented loading of deeper local history. Regarding cross-platform interaction, copying text from Codex to Slack now retains Markdown formatting, and the issue of the interface freezing when pasting large blocks of text has been fixed. Meanwhile, draft text is not lost during thread handover, and pasted image previews also support navigation using arrow keys.
OpenAI Codex's anti-abuse mechanism misjudged and caused a surge in credit limits, prompting the official team to reset the credit limits for all users.
According to Beating's monitoring, Tibo Sottiaux, core product lead at OpenAI, stated that due to a misjudgment by the system's built-in anti-fraud and anti-abuse mechanisms leading to accelerated depletion of user credit limits, the official team has urgently reset the usage limits for all Codex users free of charge. The abnormal credit limit depletion issue actually began around June 16th and fully erupted on social media platforms on June 25th. Hundreds of developers reported on GitHub and social media that Codex token consumption was abnormally high, with some accounts experiencing a 10 to 20 times faster depletion rate than usual. A paid user with a $200/month subscription reported that their additional $40 temporary credit limit was exhausted within 3 to 4 hours. Other developers reported that their budget, originally estimated to support 5 hours of work, was completely depleted after only a few prompt interactions. The slow response from the OpenAI development team sparked intense protests from numerous developers on social media platforms. In response to user protests, Vaibhav, a member of the OpenAI technical team, first publicly collected user feedback identification codes. Subsequently, Sottiaux acknowledged that the anti-abuse system might have made a misjudgment and promised to follow up. In the latest quota reset announcement, Sottiaux emphasized that the team had implemented initial mitigation measures. Although internal investigations showed that the affected user base was not large, the official decision was still to reset the usage limits for all Codex users free of charge and to continue monitoring the system status.
OpenAI introduces Codex's "Record and Reproduce" feature, which can directly transform demonstration workflows into AI skills.
According to Beating, OpenAI has introduced a new feature called "Record & Reproduce" for its coding agent Codex. This feature allows users to demonstrate a routine, repetitive workflow (such as filling out an expense report or submitting a leave application) to Codex, which can then transform the demonstration into a structured skill that can be reviewed and edited for automatic reuse later. Users can control the start and stop of recording. This feature is currently only available on macOS and is an optional configuration. In the initial release, it is not available in the European Economic Area (EEA), the UK, and Switzerland; furthermore, users or their administrators must grant "Computer Use" permissions to use the feature.