Writing C++ with Jev by picking valid next tokens
The author experimented with TypeSafe's Jev decision/classifier model for C++: at each step it was given only grammatically valid next tokens to pick from, avoiding free-form generation.
The author notes that about two weeks after Jev, OpenAI, Cloudflare, and AWS showed up with similar ideas; he sent roughly 50 questions for less than one cent and ran an open-source model locally while on the waitlist. The linked article covers using decision models for 8 DevOps tasks, with themes including ContextLayer, AnyAgentSameContext, and AgenticAI.
Just over two weeks after Jev, OpenAI, Cloudflare and AWS showed up with the same idea. We sent about 50 questions for less than a cent and ran an open-source model locally while waitlisted. with @cageyvdev https://getboris.ai/insights/021-8-devops-jobs-to-try-with-decision-models/… #ContextLayer #AnyAgentSameContext #AgenticAI