Konsey
Multi-LLM council where a model can't verify its own output
Konsey이란?
Trusting a single LLM to grade its own answer is a conflict of interest. Konsey runs several models as a council: independent providers each plan, an adversarial critic attacks the plans, and a different provider verifies the result. The producer never verifies its own output. Vendor-neutral (Claude/Codex/Gemini or local Ollama), local-first, layered PHI/KVKK-aware safety, MIT-licensed.
스크린샷
?
아직 댓글이 없어요. 가장 먼저 남겨보세요!
Konsey에 대한 X의 실제 대화
X에 게시