SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?
2026-09-02 · 172 min · episode 1094 · 16 entities
Asserted relationships
-
0.82
evidence rules-v5
Hosts: Steve Gibson and Leo Laporte
-
0.55
evidence rules-v5
Feed author/publisher: Leo Laporte
-
0.40
evidence rules-v5
Feed category: Technology
-
0.40
evidence rules-v5
Feed author/publisher: TWiT
-
0.40
evidence rules-v5
Feed category: Security
-
0.38
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://twit.tv/clubtwit
-
0.38
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://grc.com/sn/SN-1094-Notes.pdf
Entities found in this episode
companys 4
-
0.70
evidence rules-v5
Feed author/publisher: TWiT
-
0.50
evidence rules-v5
Feed category: Technology
-
0.40
evidence rules-v5
Feed category: Technology
-
0.40
evidence rules-v5
Feed author/publisher: TWiT
websites 4
-
0.45
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://twit.tv/clubtwit
-
0.45
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://grc.com/sn/SN-1094-Notes.pdf
-
0.38
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://twit.tv/clubtwit
-
0.38
evidence rules-v5
Link in episode "SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?": https://grc.com/sn/SN-1094-Notes.pdf
persons 3
-
0.86
evidence rules-v5
Hosts: Steve Gibson and Leo Laporte
-
0.70
evidence rules-v5
Feed author/publisher: Leo Laporte
-
0.55
evidence rules-v5
Feed author/publisher: Leo Laporte
concepts 3
-
0.50
evidence rules-v5
Feed category: Security
-
0.42
evidence rules-v5
SN 1094: AI Patching Shortcomings - Should You Trust AI-Generated Code?
-
0.40
evidence rules-v5
Feed category: Security
podcasts 2
-
0.95
evidence rules-v5
Feed title: Security Now (Audio)
-
0.82
evidence rules-v5
Hosts: Steve Gibson and Leo Laporte
Episode description as stored
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 notes (including fixes), visit Steve's site: grc.com , also the home of the best disk maintenance and recovery utility ever written Spinrite 6 .
Join Club TWiT for Ad-Free Podcasts!
Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit
Sponsors:
bitwarden.com/twit
outsystems.com/twit
threatlocker.com/twit
doppel.com