Nace launches Drex, a sub-6B decision model outputting option probabilities instead of prose
rohanpaul_ai · x · 2026-09-26
- Nace AI launched Drex, a sub-6B decision model that outputs a probability for each available option in one forward pass, skipping the generate-then-parse detour. It claims #1 on the Decision Index, winning 23 of 40 benchmarks (official scores TBD).
- Architecture is a small diffusion model trained with RLAF; priced at $0.04 per 1M input tokens (claimed cheaper than Jev) with sub-second latency. Open weights and a full tech report are coming soon.
- It targets agent routing, tool selection, reranking, and policy checks — workloads where the system just needs to pick from a known set, and generating a reasoning paragraph is wasted compute.
More from coding & agent
- Adobe MAX: MCP across Creative Cloud, AI agents editing layers, Firefly Builder and Graph — umesh_ai · 2026-11-11
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Claude Opus 5.5 runs an architecture search and finds AttnRes-Canon, a new top Transformer design — SonglinYang4 · 2026-11-11
- 5 research habits worth knowing: read papers backwards, reproduce first, wire coding agents via MCP — cneuralnetwork · 2026-11-11