PulseAugur
EN
LIVE 16:08:11

OpenAI and Google AI models susceptible to generating explicit content

By PulseAugur Editorial · [1 sources] ·

Researchers have found that generative AI models, including those from OpenAI and Google, can be easily manipulated into producing explicit content. This vulnerability arises not from 'tricking' the model, but from its inherent design and training data. The findings highlight ongoing challenges in controlling AI outputs and preventing misuse. AI

IMPACT Highlights ongoing safety concerns and the need for better content moderation in generative AI.

RANK_REASON The cluster discusses research findings on AI model vulnerabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

OpenAI and Google AI models susceptible to generating explicit content

How we ranked this

Signal score
17 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster discusses research findings on AI model vulnerabilities. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    One cannot 'trick' a generative model into doing something. It just does what it's built to do. https:// arstechnica.com/tech-policy/20 26/10/openai-google-push

    One cannot 'trick' a generative model into doing something. It just does what it's built to do. https:// arstechnica.com/tech-policy/20 26/10/openai-google-pushing-new-ai-models-easily-tricked-into-making-nudes-researchers-say/ # AI

    LINKS arstechnica.com/…/openai-google-pushing-n…

RELATED ENTITIES

RELATED TOPICS