Agentic backdoors via pretraining poisoning

Article URL: https://arxiv.org/abs/2610.37741 Comments URL: https://news.ycombinator.com/item?id=50341334 Points: 84 # Comments: 28

Read the full story at Hacker News Front Page ↗

Timeline · 1 report

2026-11-02 18:30 · Hacker News Front Page
Agentic backdoors via pretraining poisoning

More stories

Schools Will Lose Google Search If They Say No To Google AI — Forbes AI
OpenAI hires former Army Secretary Dan Driscoll as senior counselor for national security — OpenAI News
Anthropic reports $17B quarterly revenue, 1,100% surge ahead of IPO — Reuters AI
OpenAI signs four agreements with Abu Dhabi spanning energy, government and investment — Reuters AI
Apple rolls out Siri Recap and Live Rewind audio features on Apple Watch in watchOS 27 beta — Engadget
Top Anthropic product leader Cat Wu, one of the faces of Claude Code, has left the startup — Business Insider AI
Meta Launches Bond Sale to Help Fund AI Investments — Bloomberg AI
Introducing the Grid Protectors Program — OpenAI News

Get the daily brief of stories like this at 6:30 every morning →