SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?
About this episode
The episode discusses the vulnerabilities in AI-generated code and the implications for security practices.
AI-generated code is flooding the industry, but researchers reveal that almost half of it contains critical vulnerabilities. This week, we unpack what happens when the race for automation outpaces security best practices. A possible means for preventing prompt injection abuse. Clear evidence of Chinese-made router malicious intent. A cool before and after SpinRite graph of SSD performance. How about adding unpredictable hashes to role tags? What did Claude make of last week's podcast? Could much better harnesses prevent prompt injection? A listener wants us to stop saying AI "thinks". AI designers ignore well-understood security concepts. Can we explain LLM AI using conventional computer terms? A listener strongly dislikes the term "rotating credentials". The land of AI is being filled with "meat proxies". Researchers exhaustively test frontier model vulnerability remediation. (hint: It does not go well.) Show Notes - https://www.grc.com/sn/SN-1094-Notes.pdf Hosts: Steve Gibson and Leo Laporte Download or subscribe to Security Now at https://twit.tv/shows/security-now . You can submit a question to Security Now at the GRC Feedback Page . For 16kbps versions, transcripts, and…
People in this episode
Hosts: Steve Gibson, Leo Laporte
Mentioned in this episode
Organizations: Chinese, GRC, TWiT
Products: SpinRite
More episodes of Security Now (Video)
- SN 1095: AI-Driven Expertise Loss - Gemini, Hugging Face, and the AI Arms Race
- SN 1093: Tokens in the Stream - Why LLMs are inherently insecure and prompt injection will persist
- SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails
- SN 1091: The Post BlackHat State of AI - When AI Writes Malware
- SN 1090: Black Hat - The Hidden Flaws in AI Security Nobody Saw Coming
- SN 1089: Models Go Rogue & ExploitGym - Regulators, Start Your Engines
Explore listener stats, chart rankings, contacts and more on the Security Now (Video) podcast page.