The Jev meme now has an OpenAI-compatible completions API and scores 56.7% on next-character prediction
AlexandrePesant · x · 2026-09-21
The community meme 'Jev' now ships a completions API and Playground: an 'autoregressive decision model' that calls Jev once per character over the bare alphabet with no dictionary behind it. It offers OpenAI-compatible /completions, /chat/completions and /models endpoints with streaming and logprobs, and names the next character correctly 56.7% of the time on 60 held-out prose cuts, versus 86.7% for a frontier model. Impossible options are pruned from the answer set rather than answered for it.
More from coding & agent
- Dev vibe-codes a living-room wall game with Codex, controlled by hand gestures — tristanbob · 2026-09-22
- A developer built an independent quality-and-popularity index for MCP servers — Prestigious-Web-2968 · 2026-09-22
- GitHub Copilot desktop app to get editable diffs for agent-generated changes — mariorod1 · 2026-09-22
- Dev builds AI Scene Director on JEV: one prompt rewrites Three.js scene — jamestagg · 2026-09-22
- Why your agent keeps resurrecting blockers from tasks fixed weeks ago — Lopsided_Manner_7602 · 2026-09-22
- ProgramAsWeights demos: six neural programs compiled from English, powered by Qwen3 0.6B — yuntiandeng · 2026-09-22