Labrin

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.

GPT-Realtime-2 for instantly translating audio in realtime

I just added real-time AI translation into Chormex using GPT-Realtime-2… and this feels absolutely surreal. It works across YouTube videos, live streams, meetings, presentations, basically anywhere audio is playing inside Chrome. You can watch translated speech in real time while simultaneously using Codex on top of the live context. “Summarize this.” “What are the key points?” “Turn this into notes.” “Explain what they mean.” “Organize the discussion.” …all while the video or meeting is still happening. It genuinely feels like browsers are evolving into real-time AI operating systems. We are getting dangerously close to a world where language barriers on the internet completely disappear.

Codex 5.5 hack: "Are you 100% confident in this strategy? If not, find all possible loopholes, suggest proper fixes and run this loop until you are factually 100% confident in the new startegy" This works like charm. It makes Codex 5.5 high perform even better than codex 5.5 extra high. Why? Codex 5.5 is the only model i noticed that is self aware. It never makes high claims unless the model verifies everything. This doesn't work with Opus 4.7 cuz that's a very insecure model. You can paste this prompt over and over again, the model keeps saying "you're absolutely right,....." But with codex, after 2-3 iterations you'll notice yourself it actually patched all loopholes and this genuinely sounds like a good strategy. Try this out, thanks me later.

OpenAI 在 API 里发布了 GPT-Realtime-2。 可以理解为：语音 Agent 换上了一颗更强的大脑。 以前的语音助手，大多是： 用户说话 → 转文字 → 大模型回答 → 合成语音。 能做简单问答，但一进真实业务场景就容易暴露问题：延迟高、上下文断裂、无法稳定调用系统、复杂任务处理能力不足。 这次更新的重点，是 OpenAI 把实时语音能力拆成了三块底座： 【1】GPT-Realtime-2 给语音 Agent 用。 适合客服、销售、企业助手、语音 Copilot。 它可以边听边理解，边推理边调用工具，把“对话”推进成“任务执行”。 【2】GPT-Realtime-Translate 给实时语音翻译用。 适合跨境客服、国际会议、直播翻译、在线课程。 海外用户讲英文，客服听中文；客服讲中文，用户听英文。 【3】GPT-Realtime-Whisper 给实时转写用。 适合会议字幕、直播字幕、电话质检、销售通话分析。 语音不再只是录音文件，而是可以进入 CRM、工单、纪要、质检系统的实时数据流。 开发者怎么选： 做语音 Agent → GPT-Realtime-2 做实时翻译 → GPT-Realtime-Translate 做实时字幕/转写 → GPT-Realtime-Whisper 接入方式： WebRTC：浏览器、移动端 WebSocket：服务端音频流、电话系统、直播管线 SIP：呼叫中心、传统电话网络 这次最重要的信号是： 语音 AI 正在从“对话界面”走向“业务入口”。 下一代语音产品，拼的不是声音多像真人，而是它能不能在真实对话里查系统、调工具、走流程、把事情办成。