Skip to content
Tech News
clear
Topics: Today This Week This Month This Year
91.
Microsoft, Salesforce Patch AI Agent Data Leak Flaws (darkreading.com)
92.
Researchers detail how a prompt injection attack bypassed Apple Intelligence protections (9to5mac.com)
93.
Max severity Flowise RCE vulnerability now exploited in attacks (bleepingcomputer.com)
94.
PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free (news.ycombinator.com)
95.
Artemis 2 Crew Become First Humans to Travel Beyond Earth Orbit Since the 1970s (gizmodo.com)
96.
Show HN: Zerobox – Sandbox any command with file, network, credential controls (news.ycombinator.com)
97.
Show HN: Zerobox – Sandbox any command with file and network restrictions (news.ycombinator.com)
98.
Critical Fortinet Forticlient EMS flaw now exploited in attacks (bleepingcomputer.com)
99.
Critical Flaw in Langflow AI Platform Under Attack (darkreading.com)
100.
"Disregard That" Attacks (news.ycombinator.com)
101.
CO<sub>2</sub> subsurface mineral storage by its co-injection with recirculating water (feeds.nature.com)
102.
Anthropic hands Claude Code more control, but keeps it on a leash (techcrunch.com)
103.
UV resin injection cures ancient, cataract-inflicted CRT monitor — repaired 20-inch Trinitron would have been an enviable display in the mid 1990s (tomshardware.com)
104.
Can you get root with only a cigarette lighter? (2024) (news.ycombinator.com)
105.
Snowflake AI Escapes Sandbox and Executes Malware (news.ycombinator.com)
106.
'Claudy Day’ Trio of Flaws Exposes Claude Users to Data Theft (darkreading.com)
107.
Agent Skills – Open Security Database (news.ycombinator.com)
108.
SQLi flaw in Elementor Ally plugin impacts 250k+ WordPress sites (bleepingcomputer.com)
109.
The biggest AI threats come from within - 12 ways to defend your organization (zdnet.com)
110.
macOS code injection for fun and no profit (2024) (news.ycombinator.com)
111.
Cold-injection synthesis of highly emissive perovskite nanocrystals (feeds.nature.com)
112.
ChatGPT's new Lockdown Mode can stop prompt injection - here's how it works (zdnet.com)
113.
HackMyClaw (news.ycombinator.com)
114.
Microsoft Added AI to Notepad and It Created a Security Failure Because the AI Was Stupidly Easy for Hackers to Trick (futurism.com)
115.
These 4 critical AI vulnerabilities are being exploited faster than defenders can respond (zdnet.com)
116.
Is a secure AI assistant possible? (technologyreview.com)
117.
Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for (venturebeat.com)
118.
Bots on Moltbook Are Selling Each Prompt Injection “Drugs” to Get “High” (futurism.com)
119.
I hacked my own computer using OpenClaw and it was terrifyingly easy (androidauthority.com)
120.
Autonomous cars, drones cheerfully obey prompt injection by road sign (news.ycombinator.com)
Today's top topics: openai anthropic apple ai safety google ios 27 dario amodei nvidia iphone 18 pro artificial intelligence
View all today's topics →