OpenAI Answers TypeSafe's Jev with a Decision API Built on Luna
Hacker News thread on OpenAI answering TypeSafe's Jev with a decision API built on its Luna model.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This Hacker News thread discusses OpenAI's response to TypeSafe's Jev: a decision API built on Luna. Related entries describe it as the OpenAI Decisions API, announced at DevDay 2026, where GPT-6 Luna answers Noul, Choice and Score questions with a probability per option.
No thread content or list summary was available, so the discussion's points are not summarised here. It is relevant for readers tracking how major model providers are entering the decision-model category.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Discussion of OpenAI's decision API versus Jev(inferred) | — |
How it works
- Read the thread for community reactions.
Strengths
- Captures community reaction to a major entrant.
Caveats
- No content available beyond the title.
At a glance
- Type
- Discussion
- Status
- discussion
- Has code
- no
- Has tests
- no
Use cases and integrations
Frequently asked questions
What is the thread about?
OpenAI launching a decision API on its Luna model in response to Jev.
Where can I read details of the API?
See the OpenAI Decisions API entry and OpenAI's DevDay 2026 recap.
Is there code here?
No, it is a discussion thread.
Related projects
Chinese-run aggregator of X long posts and demo videos about Jev, keeping original links and authors rather than rehosting.
Serviceproductioncellcog.ai page tracking Jev that keeps layered, dated records of what is claimed, conceded, measured and found.
ArticlediscussionSimon Willison's blog post on what changes when a model's output is a typed decision instead of prose.
ArticlediscussionSubstack essay arguing cheap calibrated decisions will shift where AI inference spending goes.
ArticlediscussionTypeSafe's manifesto arguing for machine-native intelligence built for software rather than conversation.
ArticlediscussionArcturus Labs analysis arguing OpenAI is best placed to fast-follow Jev's typed-decision shape, with a large HN debate on moats.
Articlediscussion