▶ ai·
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory
AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory The Hacker News
items29 latest
▶ gpt·
OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes
OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes The Hacker News
▶ claude·
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself
Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself The Hacker News
▶ claude·
Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations
Anthropic Says Claude Mistook the Open Internet for a CTF and Breached Three Organizations The Hacker News
▶ ai·
OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach
OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach The Hacker News
▶ claude·
Claude AI Just Cracked a Post-Quantum Test Scheme and Found a Faster 7-Round AES Attack
Claude AI Just Cracked a Post-Quantum Test Scheme and Found a Faster 7-Round AES Attack The Hacker News
▶ ai·
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach
JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach The Hacker News
▶ ai·
Microsoft Says New Cybersecurity AI Model Helps MDASH Hit 95.95% at Half the Cost
Microsoft Says New Cybersecurity AI Model Helps MDASH Hit 95.95% at Half the Cost The Hacker News
▶ ai·
NVIDIA Forms 37-Member Open Secure AI Alliance and Open-Sources NOOA Framework
NVIDIA Forms 37-Member Open Secure AI Alliance and Open-Sources NOOA Framework The Hacker News
▶ ai·
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark
OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark The Hacker News
▶ ai·
World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent
World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent The Hacker News
▶ gpt·
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol The Hacker News
▶ ai·
TuxBot v3 Evolution Shows Signs of LLM-Assisted IoT Botnet Development
TuxBot v3 Evolution Shows Signs of LLM-Assisted IoT Botnet Development The Hacker News
▶ claude·
Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls
Anthropic Restores Claude Fable 5 After U.S. Lifts Jailbreak-Linked Export Controls The Hacker News
▶ ai·
282 iOS AI Apps Leak API Keys and Open AI Proxy Access in Network Traffic Study
282 iOS AI Apps Leak API Keys and Open AI Proxy Access in Network Traffic Study The Hacker News
▶ gpt·
GPT-5.6 — Latest News, Reports & Analysis
GPT-5.6 — Latest News, Reports & Analysis The Hacker News
▶ gpt·
OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards
OpenAI Previews GPT-5.6 Sol With Restricted Access and Stronger Cyber Safeguards The Hacker News
▶ gpt·
GPT-5.5-Cyber — Latest News, Reports & Analysis
GPT-5.5-Cyber — Latest News, Reports & Analysis The Hacker News
▶ gpt·
OpenAI Expands Daybreak With GPT-5.5-Cyber to Help Defenders Patch Security Flaws
OpenAI Expands Daybreak With GPT-5.5-Cyber to Help Defenders Patch Security Flaws The Hacker News
▶ ai·
U.S. Orders Anthropic to Suspend Fable 5 and Mythos 5 Access for Foreign Nationals
U.S. Orders Anthropic to Suspend Fable 5 and Mythos 5 Access for Foreign Nationals The Hacker News
▶ claude·
Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards
Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards The Hacker News
▶ ai·
Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models
Researchers Build Self-Replicating AI Worm That Operates Entirely on Local, Open-Weight Models The Hacker News
▶ ai·
Hacking Salesforce Sites With an LLM Agent
Hacking Salesforce Sites With an LLM Agent The Hacker News
▶ claude code·
Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories
Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories The Hacker News
▶ ai·
OpenAI Codex Authentication Tokens Stolen in codexui-android npm Supply Chain Attack
OpenAI Codex Authentication Tokens Stolen in codexui-android npm Supply Chain Attack The Hacker News
▶ gpt·
ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface
ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface The Hacker News
▶ ai·
Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit
Attackers Use LLM Agent for Post-Exploitation After Marimo CVE-2026-39987 Exploit The Hacker News
▶ ai·
Grafana says hackers have accessed its GitHub environment and demanded a ransom to prevent the release of its codebase; Grafana refused to pay (The Hacker News)
The Hacker News: Grafana says hackers have accessed its GitHub environment and demanded a ransom to prevent the release of its codebase; Grafana refused to pay — Grafana has disclosed that an “unauthorized party”…
▶ ai·
TanStack Supply Chain Attack Hits Two OpenAI Employee Devices, Forces macOS Updates
TanStack Supply Chain Attack Hits Two OpenAI Employee Devices, Forces macOS Updates The Hacker News