Introducing System One Models and Jev (Hacker News)
Hacker News launch thread for Jev, about 1,800 points, debating whether typed decisions can replace LLM calls.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
This is the Hacker News discussion of TypeSafe's launch post introducing System One models and Jev. The lists record it at roughly 1,800-1,862 points with around 480 comments, which they describe as mostly positive.
The thread's central debate is whether typed decisions, where a model returns probabilities over allowed answers instead of generating text, can replace LLM calls for classification, routing, scoring and verification. It is useful for seeing early practitioner reactions, objections and comparisons with classical classifiers and prompted LLMs. The comments were not fetched here, so individual arguments are not summarised.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Can typed decisions replace LLM calls for classification, routing and verification?(inferred) | — |
How it works
- TypeSafe's launch post is shared on Hacker News
- Commenters debate use cases, limits and alternatives
- Readers weigh typed decisions against LLM calls for their own tasks
Strengths
- Large, broad sample of practitioner opinion at launch
Caveats
- Opinions, not measurements
- Early reactions may predate later model versions
At a glance
- Type
- Discussion
- Status
- discussion
- Has code
- no
Use cases and integrations
How curated lists describe it
Hacker News: 1,800-point launch thread whose ~480 comments debate whether typed decisions replace LLM calls for classification, routing, and verification.
yibie/awesome-jev**1862 points**; mostly positive comments.
wh000wh000/awesome-jev-live1,800-point thread debating whether typed decisions replace LLM calls for classification, routing, and scoring.
hellogumbo/awesome-jev
Frequently asked questions
What is this thread?
The Hacker News discussion of Jev's launch, with about 1,800 points per the lists.
What do commenters debate?
Whether typed decisions can replace LLM calls for classification, routing, scoring and verification.
Is it a technical source?
It is a discussion; use the launch post and docs for technical detail.
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