一篇读懂训练稳定性：Loss Spike、梯度爆炸与数值问题的诊断与修复
从 PaLM 与 OPT 的真实病历出发，拆解 loss spike 的五类根因、回滚跳批的标准操作与 z-loss、软截断等预防手段。
阅读全文 →
全部文章
ARCHIVE 共 463 条Deepmind was built to chase AGI, but its new chief just wants Gemini 4 out the door
Sep 24, 2026
Koray Kavukcuoglu wants to release Gemini 4 well before the end of the year. He calls the AGI question, whi…
Google's new Flash TTS models let you design AI voices from scratch using text descriptions
Sep 23, 2026
Nano Banana Pro prompted by THE DECODER
Key Points
Google has released two new text-to-speech models, Gemin…
GPT-6之后，具身智能走向何方？诺因发布GLOW技术报告，给出机器人“一教就会”的答案
量子位的朋友们* 2026-09-24 16:20:12 来源：量子位
人类演示一次，机器人即可实现跨场景任务复用
一直以来，要让机器人学会一项新任务，往往需要重新采集数据、编写固定流程，或进行针对性训练。这类方式可以解决确定性较高的任务…
Google Releases Gemini 3.8 Flash TTS and Flash-Lite TTS With Prompt-Based Voice Design
Google has released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, 2 new text-to-speech models in its Gemini Audio …
How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure
Evaluations of LLM systems routinely average over small prompt sets and report models as a ranked table. We ask how much…
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs
While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit f…
ChatGPT Voice gets closer to "Her" with email, calendar, and Slack access
Sep 23, 2026
ChatGPT Voice gets a major upgrade.** The globally available voice feature now runs on OpenAI's new GPT-6 A…
Alibaba launches Qwen Audio 3.1 with new models and slashes AI audio prices by up to 95 percent
Sep 23, 2026
Alibaba's AI team Qwen has released Qwen-Audio-3.1, a lineup of five models for speech recognition (ASR), t…
斑马智能发布端模型AutoOmni2.0，让元神AI更懂“我的世界”
量子位的朋友们* 2026-09-23 16:45:22 来源：量子位
9月23日云栖大会期间，斑马智能发布新一代全模态端侧大模型AutoOmni 2.0-23B-A3B
9月23日云栖大会期间，斑马智能发布新一代全模态端侧大模型Auto…
OpenAI launches GPT-6 Sol and Luna, boasting lower cost and fewer mistakes
Earlier this month, OpenAI launched GPT-6 Astra, which it heralded as its most powerful and capable model yet, and the “…
实时世界模型进入“全科生”阶段，PixVerse R2先交卷！
梦瑶* 2026-09-23 14:08:50 来源：量子位
实时性和通用能力，世界模型可以全都要
这年头，实时生成的世界模型越来越会「造世界」了。
画面更夯，控制更细，但一旦走到实时生成这一步，继续往上做能力，就会有个很难绕开的坎：
能…
OpenAI 发布 GPT-6 Sol 和 Luna 模型，API 价格大降 50%
IT之家 9 月 23 日消息，OpenAI 今日发布 GPT-6 系列模型的最新成员 **GPT-6 Sol 和 GPT-6 Luna**。
OpenAI 官方表示，两款模型采用与 GPT-6 Astra 类似的方法进行训练，将 Astr…