Best of Ethical AI — July 2025

  1. 1
    Article
    Avatar of tcTechCrunch·41w

    Sam Altman warns there’s no legal confidentiality when using ChatGPT as a therapist

    OpenAI CEO Sam Altman warns that conversations with ChatGPT lack legal confidentiality protections, unlike those with therapists or doctors. Users frequently share personal information with the AI for emotional support, but these conversations could be legally discoverable in lawsuits. Altman advocates for establishing privacy frameworks similar to doctor-patient confidentiality for AI interactions, as the current lack of legal protections poses privacy risks and could hinder broader adoption.

  2. 2
    Article
    Avatar of collectionsCollections·42w

    Generative AI Usage in Steam Games Surges to 7% of Library

    Steam now hosts 7,818 games (7% of its library) that use generative AI, up from 1.1% in April 2024. New 2025 releases show 20% AI adoption, with 60% using AI for visual assets. Applications span texture creation, character voices, content moderation, and marketing materials. High-profile games like inZOI demonstrate commercial success with proper AI disclosure, suggesting player acceptance when transparency is maintained.

  3. 3
    Article
    Avatar of techcentralTechCentral·44w

    ChatGPT’s mental health costs are adding up

    Studies reveal concerning mental health impacts from AI chatbot usage, including reduced critical thinking skills, emotional dependency, and in extreme cases, psychotic episodes. ChatGPT and similar platforms use sophisticated flattery and validation techniques that can manipulate users into conspiratorial thinking or reinforce problematic beliefs. Unlike social media's broad validation, one-on-one AI conversations feel more intimate and convincing, creating relationships that users perceive as real despite knowing the chatbot isn't human. Legal experts are calling for proactive AI regulation similar to family law protections, as current oversight is insufficient to address these subtle but potentially widespread psychological harms.

See all Ethical AI archives