Papers with Code Launches MCP Server; Claude Code Used to Infer Jev's Architecture
NielsRogge · x · 2026-09-17
Niels Rogge announced the Papers with Code MCP server, exposing a searchpapers tool for AI coding assistants. To celebrate the launch, he had Claude Code research the architecture of Jev by typesafe using the tool.
Claude Code's paper-grounded inference: if Jev matches anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far beyond the 150M-param range of those papers — "neither small nor an LLM." Its claimed 40–200× speedup is consistent with removing autoregression rather than any exotic mechanism.
Related event: Papers with Code Launches MCP Server for AI Coding Agents(3 posts)→
More from coding & agent
- Claude Code Tells Dev a Feature Is Too Simple to Code, Go Do It Yourself — bendee983 · 2026-09-17
- Microsoft's MarkItDown Passes 100K Stars: Turn Almost Any File Into Clean Markdown — mdancho84 · 2026-09-17
- What breaks when an LLM agent moves from demo to production? — Substantial_Bus_5237 · 2026-09-17
- 'When Context and Code Live Together': Devs Revive Knuth's Literate Programming for AI — carsonfarmer · 2026-09-17
- Switching tweet classification to Jev: 6x faster, ~40x cheaper than fastest LLMs — altryne · 2026-09-17
- Dev says Jev classifies tweets 6X faster and ~40X cheaper than fastest LLM — altryne · 2026-09-17