Deploy Securely

Code Llama: 5-minute risk analysis

Share episode

Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.

0:00 | 4:43

Someone asked me what the unintended training and data retention risk with Meta's code Llama is.

My answer:

the same as every other model you host and operate on your own.

And, all other things being equal, it's lower than that of anything operating -as-a-Service (-aaS) like ChatGPT or Claude.

Check out this video for deeper dive?

Or read the full post on Deploy Securely: https://blog.stackaware.com/p/code-llama-self-hosted-model-unintended-training

Want more AI security resources? Check out: https://products.stackaware.com/