Why I couldn't build Jev at OpenAI
Video talk by TypeSafe founder Diogo Almeida on why Jev needed a separate company: a design rationale for System One models.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
In this YouTube talk, Diogo Almeida, TypeSafe's founder and a former OpenAI researcher, explains why he could not build Jev at OpenAI and why it had to be a separate company. According to the list summary, it is the closest thing available to a design rationale for System One models.
It is useful background for understanding why Jev returns probabilities rather than text.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Other | Not applicable; a design-rationale talk.(inferred) | — |
How it works
- Explain the limits of building decision models inside a chat-model company.
- Describe the System One design rationale.
Strengths
- First-hand rationale from the founder.
Caveats
- Video; claims are the founder's perspective.
At a glance
- Type
- Article
- Status
- discussion
- Has code
- no
- Has tests
- no
Use cases and integrations
How curated lists describe it
Video: Diogo Almeida's talk on why this had to be a separate company, the closest thing to a design rationale for System One models.
yibie/awesome-jev
Frequently asked questions
Who gives the talk?
Diogo Almeida, TypeSafe's founder.
What is it about?
Why Jev needed a separate company and the rationale behind System One models.
Where is it?
On YouTube.
Related projects
Long-form analysis of what Jev is, why it is fast, how much of the hype holds up, and how hard it is to reproduce.
ProjectdiscussionJapanese research deck, article and source ledger tracking TypeSafe's Jev and System One models over time.
ProjectdiscussionMarkdownUnofficial Jev information hub site with access guide, pricing comparison, a BYOK playground and an auto-updated news timeline.
AppproductionPythonTypeSafe's launch post for System One models and Jev, covering the interface, RLCD training, pricing, demos and caveats.
ArticleproductionLatent Space podcast episode with TypeSafe's Diogo Almeida on RLCD, intelligence per dollar, reliability and post-chat interfaces.
ArticlediscussionThe Neuron's explainer article on TypeSafe's Jev and System One models: AI decisions without a chatbot.
Articlediscussion