#spec

OpenAI Updates Its Model Spec

The Model Spec is potentially OpenAI’s most important document. It outlines what they aspire for the model to do, and how it should think. I’ve already covered a previous version in depth , so my strategy this time is to look at the diff. I had a Google Doc created for this purpose , and will be working from there. A bunch of things get moved around or reworded, often piecemeal. There are a lot of line edits, most of which are improvements. I’m focusing on what looks new and important. My main new critique is that many of the new examples do not carve reality at its joints, instead having over

LessWrong · EN

Show HN: Provenance – A Spec That Evolves with Your Code

Hi all, I've been building Provenance, a tool for growing your specification of your code as your understanding of it becomes clearer. Currently I feel that the lifecycle around software improving feels too detached. We talk to our teams, spec things out with our agents, track work in tickets, but there's nothing really to connect it all together and there's no neat way to keep it all updated. Provenance is my attempt to solve that problem by building direct links between planning, requirements, implementation, and verification. I've purposely tried to keep the concepts as agnostic to everyone

Show HN · EN

OpenAI réorganise son Model Spec

Le 29 octobre 2026, OpenAI a dévoilé une révision importante de son Model Spec. Ce référentiel public, qui encadre la (...)

Le Monde Informatique · FR