Theo slams OpenRouter for using Jev: a non-reasoning classifier that can't gauge task complexity
intellectronica · x · 2026-09-26
Theo publicly urged OpenRouter not to integrate typesafeai's Jev model. His argument: Jev is a "system one" model that categorizes rather than reasons. From a prompt alone it cannot assess real task complexity — it has zero context about the system the prompt lives in, the tools the agent can access, or the obstacles it must work around. Asked to "port this to Rust," it can't tell whether the codebase is a 100-line TypeScript file or a million-line application, nor whether a bug fix touches core complexity. That makes it unreliable for model routing in coding-agent workflows.
More from coding & agent
- Stealth model Space Bunny rebuilds entire site from a 40s screen recording — PrajwalTomar_ · 2026-09-26
- AI veteran: Agentic AI is the control harness, not a separate business opportunity — nicolaiwadstrom · 2026-09-26
- McKinsey Deck: a Claude Skill that builds editable consulting-style PPT slides — baabullah · 2026-09-26
- KoboldCpp ships built-in Agent harness; author warns of phishing site koboldcpp.com — HadesThrowaway · 2026-09-26
- Nace launches Drex, a sub-6B decision model outputting option probabilities instead of prose — rohanpaul_ai · 2026-09-26
- The team was already running LLM cross-checks on reports — the real gap was that it all lived in one person's account — beglen · 2026-09-26