‘Vibe coding’ using LLMs susceptible to most common security flaws

www.scworld.com

‘Vibe coding’ using LLMs susceptible to most common security flaws

www.scworld.com

Nemeski@lemm.ee to

Security@programming.devEnglish · 3 months ago

OpenAI’s models were most likely to produce vulnerable code in tests by Backslash Security.

You must log in or # to comment.

Chat

Security@programming.dev

security@programming.dev

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !security@programming.dev

A community for discussion about cybersecurity, hacking, cybersecurity news, exploits, bounties etc.

Rules :

All instance-wide rules apply.
Keep it totally legal.
Remember the human, be civil.
Be helpful, don’t be rude.

Icon base by Delapouite under CC BY 3.0 with modifications to add a gradient

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

16 users / day
16 users / week
16 users / month
16 users / 6 months
1 local subscriber
949 subscribers
38 Posts
0 Comments
Modlog

mods:
LinearArray@programming.dev