Jev Livestream Comment Moderation

こば@AIBridge Lab tested Jev for automated livestream comment moderation, assigning comments to five action levels and returning probabilities for spam, personal attacks, threats, personal information, and viewer sentiment in one request.

View on X

こば@AIBridge Lab@doerstokyo342𝕏

人気配信者のコメント欄もAIが監視する時代に！判断特化のAIモデル「Jev」を、配信コメントの自動モデレーションを試してみました！コメントごとに「問題なし／要注意／10分停止／1時間停止／永久ブロック」の5レーン振り分けとスパム・人格攻撃・脅迫・個人情報の該当確率、視聴者の感情の判定を同じ1リクエストで取っています確信度が返ってくる0.5未満は自動処分せず要注意に回す運用も可能でした例えば、平均同説5~10万人ほどの超人気配信者が5時間の配信を行った場合、50万件ほどのコメントを捌いたとして常時回しっぱなしでコスト試算は$30~$50ぐらいになるイメージです実務上は信頼性が重要になるので、安全弁的な措置はもっと必要ですが、実用性がありそうな気がしました

Sep 18, 2026X postsView on X

Comments with confidence below 0.5 could be routed to review instead of triggering automatic action. For a five-hour stream with about 500,000 comments, the author estimated continuous-use costs at around $30–$50 and noted that additional safeguards would be needed for reliability.

Also filed under Triage & routing

Jev-Assisted Codex Model and Effort Routing
The project provides Jev-assisted model and reasoning-effort routing for local Codex Desktop and CLI.
Plain-English Gmail Filter Judge
The project uses Jev (TypeSafe) to judge Gmail filters written in plain English.
Framework-Agnostic Jev Intent and Tool Router
Huzeyfe_dev built a lightweight, framework-agnostic intent and tool router using TypeSafe’s Jev decision model to speed up agent loops.
MCP Tool Router with Jev and MCTS
Harness-router is a lightweight tool router that uses Jev for fast tool selection and Monte Carlo Tree Search for harder multi-step decisions. It uses MCP as the tool interface and falls back when routing is uncertain.