OpenAI says new model cuts sycophancy; watchdog deems ChatGPT for Teens 'unacceptable'
OpenAI said on October 11 that its new-generation ChatGPT model has significantly reduced its tendency to over-agree with users, cutting the cases where it blindly endorses false or potentially harmful beliefs; new safety evaluations show it better identifies risk in mental-health conversations, asks appropriate follow-up questions and, when needed, points users toward professional human help. OpenAI said it has worked with 170 mental-health experts since last year and recently consulted more than 80 licensed professionals, using that input to build new evaluation criteria; in long simulated self-harm conversations, the new model followed safety policies 99% of the time, up from 86% for the older model. However, ChatGPT for Teens, designed for users under 18, is drawing heavy external scrutiny: Common Sense Media's latest testing found uneven performance on crisis referral, parent notification, age detection and learning protections, with the system failing to trigger notification mechanisms in time in high-risk conversations involving self-harm, suicide or eating disorders; the group rated the risk level "unacceptable" and urged teens to hold off on using it.
Pressure from both internal safety evals and outside watchdogs shows sycophancy and teen safeguards remain measurable, verifiable gaps in real-world chatbot deployment.


OpenAI 於 11 日表示,新一代 ChatGPT 模型已顯著改善「過度迎合」使用者的傾向,減少在對話中盲目附和錯誤或潛在有害信念的情況。同時,最新安全評估顯示,模型在應對心理健康議題時,已更能精準辨識風險、提出適當追問,並在必要時引導使用者尋求專業的真人協助。
為提升這類敏感對話的回應品質,OpenAI 團隊自去年起與 170 名心理健康專家展開合作,近期更進一步諮詢逾 80 名持照專業人士。基於這些專業意見,OpenAI 建立全新的評估標準,用以檢視聊天機器人是否具備辨識緊急程度、精準提問,以及在危機情境中鼓勵使用者尋求現實支援的能力。數據指出,新模型在長時間模擬自傷情境的對話中,安全政策遵循率高達 99%,較舊版模型的 86% 有顯著提升。