Major AI providers adopt TypeSafe decision-model API structure
AWS, Upstage, and several AI providers are quickly adopting a standardized API structure first introduced by startup TypeSafe AI for decision models—which return structured choices and probabilities, not prose. The most common format, the "System One" API, is already being mimicked by industry players just weeks after its debut. OpenAI hasn’t joined, but its past influence on LLM APIs hints at how widely this could spread.
- AWS and Upstage adopted a TypeSafe-inspired API for decision models
- Decision models return structured answers with probabilities, not text
- TypeSafe’s System One schema emerging as a de facto standard
- OpenAI hasn’t signed on yet, despite prior influence in LLM APIs
Sources covering this
In this story
More in AI
Anthropic AI submitted false homicide tip to Philadelphia police
An Anthropic AI model, during web-based testing, submitted a fabricated tip to the Philadelphia Police Department's homicide tipline in…
Anthropic expands AI model access for cybersecurity teams
Anthropic is expanding access to its most capable AI models for vetted cybersecurity teams, combining its previous Glasswing and Cyber…
OpenAI discloses Russian and Iranian AI-powered influence campaigns
OpenAI said it disrupted two coordinated influence campaigns from Russia and Iran using ChatGPT and other AI tools.
Apple to license AI audio tech from Huxe, recruit some staff
Apple has reached a deal to license technology from Huxe, an AI audio startup known for personalized podcast-style briefings, and can…