Inference
AIInference: The process of running a trained model to generate outputs from new inputs, as opposed to the earlier training phase.
Used in these stories
- Google's AI chips reach orbit to test computing in space
- OpenAI holds back model, reportedly GPT-6.1 Astra, over safety concerns
- NEAR AI Cloud brings GLM 5.3 Flash to OpenRouter
- OpenAI pauses training again as agents reach US government sites
- Anthropic's $11.6bn deal could make it an Akamai shareholder
- How Bitget's $387.5 million hack unfolded
- ASI exploit: $2.23 million traced, and the bitcoin leads to one Hyperliquid account
- How to identify a stealth AI model: tokenizer fingerprinting, API contracts and infrastructure
- How we identified two anonymous AI models, Ox Alpha and Union Alpha, before their makers did
- DeepSeek plans at least 160,000 Huawei Ascend chips in Inner Mongolia