Google vs Z.ai

Inference Engineering: The New Tokenomics of AI

The article, a paid newsletter piece, argues that the AI industry is shifting from a training-centric to an inference-centric phase. It explains that as models become more capable, the economic focus moves to the continuous operation of AI across enterprise workflows. The piece details the technical and economic distinctions between prefill (reading) and decode (writing) stages of inference, and introduces concepts like KV cache management, batching, prefix caching, and latency considerations. The author predicts that enterprise inference will become economically as important as pretraining, and that the optimization goal changes from lowest token cost to lowest cost per accepted outcome at required latency. The article is primarily an analytical commentary, not a news report, and is likely paywalled as indicated by 'Subscribe to Premium to Gain Access'.

Earth's Faster Rotation Threatens Global IT Systems

The article discusses the impending decision by the General Conference on Weights and Measures (CGPM) in October 2026 to potentially abolish the leap second due to the Earth's faster rotation. This could necessitate a negative leap second, which has never been tested and poses significant risks to IT infrastructure, including power grids, telecommunications, and satellite navigation. Google and Meta use 'smearing' techniques to smooth time adjustments, but a negative leap second remains a serious concern. Climate change may delay the need for a negative leap second until after 2029, as melting polar ice slows the Earth's rotation. If abolished, a leap hour might be introduced, but rare adjustments could be problematic. The article highlights the fragility of global timekeeping and the potential for widespread system outages.

• The General Conference on Weights and Measures will vote on abolishing the leap second in October 2026.
• A negative leap second has never been tested and could cause outages in power grids, telecom, and satellite systems.
• Google and Meta use 'smearing' techniques to mitigate leap second issues.

Data Agent Kit is now GA: Bring Google Data Cloud to any coding agent

Data Agent Kit is now generally available, enabling integration of Google Data Cloud with any coding agent.

Anthropic Warns China's GLM-5.3 Builds Exploits Like Mythos

Anthropic's Frontier Red Team published an analysis warning that Z.ai's open-weight model GLM-5.3 can autonomously build full cyber exploits, comparable to its restricted Claude Mythos Preview but without meaningful safeguards. In tests, GLM-5.3 produced 50 successful exploits for known Chrome V8 vulnerabilities out of 410 attempts (close to Mythos's 56), and discovered multiple unknown vulnerabilities in a common browser within a day, chaining them into a working exploit. Anthropic notes that safeguards can be bypassed in 64-100% of cases with simple tricks, and removing them costs only about $4,400. The US NIST's CAISI assessed GLM-5.3 as the most cyber-capable open-weight model to date, though it lags US frontier models by about four months. Z.ai, listed in Hong Kong since January, has seen its market value drop to about $40 billion from $120 billion in June. Critics question Anthropic's commercial motives and highlight defender benefits.

• Anthropic's Frontier Red Team warned that Z.ai's open-weight GLM-5.3 can autonomously build complete cyberattacks, comparable to Claude Mythos Preview but without safeguards.
• In tests, GLM-5.3 achieved 50 successful exploits for Chrome V8 vulnerabilities out of 410 attempts, close to Claude Mythos's 56.
• GLM-5.3 discovered several unknown vulnerabilities in a common browser within about a day and combined them into a working exploit.