Termsslug: inference-time-compute

Inference-time Compute

推理时计算

The process of consuming computational resources during model execution to optimize result quality or speed.

Curated Intelligence

2 items · Page 1/1
Hacker News AIT2·Tools
68 pts
OpenAI Launches Decisions API for 10x Faster Structured Outputs

OpenAI has released the Decisions API in public beta, designed to return typed answers such as probabilities, fixed choices, or rubric scores from text and images. It operates approximately 10 times faster than the Responses API and currently supports only the gpt-6-luna model. The tool aims to streamline content classification and request routing, requiring updated SDKs for integration.

OpenAI 官方博客T1·Models
35 pts
Paper: Trading Inference Compute for Robustness

This research proposes enhancing adversarial robustness by increasing inference-time compute. The core idea shifts defense burden from training to inference, leveraging extra computation for verification or correction. Details on methods, experiments, and performance trade-offs are currently missing.