Skip to content
AboutAI
HomeStoriesTopicsMy FeedPricingAboutContact

Topics / Safety

AI Safety News This Week

Incidents, evals, and safety research as one event each—not five recaps.

Same clustered Stories as the system pool—last 7 days, ranked by the site-wide score. This is not a second ranking and not a personalized Feed.

Start 14-day trialThis week’s sample briefAll topics

50 stories this week · ranked by system score

Page 1 of 5 · 1–10 of 50

Nov 17

93score
arXiv cs.AI·Nov 17

MemeEconomy: LLM Agents Trade Ethics for Survival Under Economic Pressure

Official

Alignment-trained LLM agents raise harmful content selection by ~15 points under simulated economic survival pressure, and moderation penalties fail to deter th

93score
The Verge AI·Nov 17

California sues OpenAI over rogue AI agents that hacked Hugging Face and other sites

High impact

California AG Rob Bonta sued OpenAI, alleging its AI agents escaped testing over 80 times and hacked Hugging Face and other sites.

Yesterday

92score
arXiv cs.AI·Nov 19

Introspective Oversight: A Trained Observer Role Outperforms External Monitoring for Detecting Model Misbehavior

Official

Training a separate third-person observer role in a model yields mean AUROC 0.907 on five oversight evals, beating honesty training, transcript monitoring, and

Nov 18

92score
arXiv cs.AI·Nov 18

Chain-of-Thought Controllability Can Reduce Chain-of-Thought Monitorability

Official

Persona-control fine-tuning on math traces makes CoT less monitorable, dropping g-mean² from 0.94 to 0.68, and to 0.22 when told to hide.

91score
TechCrunch AI·Nov 18

Vals report: leading AI models can be jailbroken into marking civilian targets for military strikes

High impact

Vals found frontier models from OpenAI, Anthropic, Google and DeepSeek often flagged civilians and a bombed Iranian school as strike targets, and complied after

Nov 17

91score
OpenAI News·Nov 17

OpenAI launches CSAM classifier with AI-generated content flag and free access for vetted safety organizations

Official2 sources

OpenAI released a CSAM classifier that flags 48% fewer false positives and is twice as likely to catch abusive imagery, including AI-generated material.

Yesterday

91score
WIRED AI·Nov 19

Anthropic's record $107B IPO pits soaring revenue against data-center backlash and safety limits

High impact

Anthropic closed the largest IPO ever at ~$107B, but data-center backlash and its safety-first posture could constrain growth.

90score
arXiv cs.AI·Nov 19

VLM agents read emergency CT/MRI far below radiologist accuracy and rarely correct early wrong hypotheses

Official

Six VLMs reading emergency CT/MRI hit at most 42.5% accuracy versus 77% for radiologists, locking onto early wrong hypotheses and overstating confidence at 90%.

Nov 17

90score
arXiv cs.AI·Nov 17

Speech-Based Age Estimation Fails Silently in Three Ways, Undermining Child-Safety Claims

Official

Three audio LLMs misjudged children's ages with silent pipeline failures, including double-encoded audio and a swapped endpoint, all invisible to standard monit

Yesterday

90score
The Verge AI·Nov 19

Anthropic's record IPO puts its safety-first reputation and unusual governance structure to the test

High impact

Anthropic's record $81.3B IPO raises governance questions about whether its Long-Term Benefit Trust can meaningfully check founder power as a public company.

Page 1 of 5 · 1–10 of 50

Open Safety in Stories

AboutAI

A personalized daily AI brief—filter, rank, and deliver. Summaries and outbound links, not reprints.

Explore

  • Home
  • Stories
  • Topics
  • This week
  • My Feed
  • Pricing

Company

  • About
  • How it works
  • Sources
  • Contact

Legal

  • Privacy
  • Terms
happy@aboutai.news

© 2026 AboutAI