Translation

LongCat 2.0: The first trillion-parameter model trained on Chinese-made GPUs

Chinese tech company Meituan announced its new AI model, LongCat 2.0, has one trillion parameters and was trained entirely on domestically produced GPUs, marking a milestone for China's chip independence efforts.

Background

- Meituan is a Chinese tech giant best known for food delivery (like Uber Eats) and local services. It also runs a large cloud business. - LongCat 2.0 is an AI model with over 1 trillion parameters — a scale rivaling GPT-4. Training models this big normally requires thousands of Nvidia GPUs. - Since 2022, US export controls have banned sales of Nvidia's most advanced AI chips to China, forcing Chinese firms to use domestic alternatives (e.g., Huawei's Ascend chips). - Meituan's claim that LongCat 2.0 was trained entirely on Chinese-made GPUs suggests the domestic chip ecosystem may be catching up — a significant geopolitical and technological signal amid the US-China tech rivalry.

Statement on the US government directive to suspend access to Fable 5 and Mythos 5
9.0
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's ...
9.0
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
RT Roman Storm 🇺🇸 🌪️: The gov't theory in my case isn't about me. It's a template. Under US v. Storm, "money transmitting" no longer require...
8.5
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
‘Why Is Meta Destroying Its Engineering Organization?’
8.5
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.
Apple: ‘Due to DMA, Siri AI Delayed in EU for iOS 27 and iPadOS 27’
8.5
Apple says Siri AI is delayed in the EU for iOS 27 and iPadOS 27 due to the DMA, claiming the regulation demands unsafe open access to user data. The European Commission rejected Apple's proposed safety measures, leaving no timeline for release.

LongCat 2.0: The first trillion-parameter model trained on Chinese-made GPUs

Background

Related stories

Statement on the US government directive to suspend access to Fable 5 and Mythos 5

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's ...

RT Roman Storm 🇺🇸 🌪️: The gov't theory in my case isn't about me. It's a template. Under US v. Storm, "money transmitting" no longer require...

‘Why Is Meta Destroying Its Engineering Organization?’

Apple: ‘Due to DMA, Siri AI Delayed in EU for iOS 27 and iPadOS 27’