Ramses Lopez
@ramses-lopez.bsky.social
Reposted by Ramses Lopez
After a deep dive on LLM agent security, here's things I think we should all be doing but aren't:
1. Running agents on remote containers only.
2. Doing internet research in a separate cleanroom env
3. Having LLMs read logs daily for signs of exfiltration/promptjacking
1. Running agents on remote containers only.
2. Doing internet research in a separate cleanroom env
3. Having LLMs read logs daily for signs of exfiltration/promptjacking
November 14, 2025 at 4:56 PM
After a deep dive on LLM agent security, here's things I think we should all be doing but aren't:
1. Running agents on remote containers only.
2. Doing internet research in a separate cleanroom env
3. Having LLMs read logs daily for signs of exfiltration/promptjacking
1. Running agents on remote containers only.
2. Doing internet research in a separate cleanroom env
3. Having LLMs read logs daily for signs of exfiltration/promptjacking
Reposted by Ramses Lopez
I read a question that I quickly replied to, but I wanted to expand on my recommendation
#Ruby #Pattern #Return #CodeDesign
What I will share here is an exploration and a proposal about how I think we can improve it:
#Ruby #Pattern #Return #CodeDesign
What I will share here is an exploration and a proposal about how I think we can improve it:
December 6, 2024 at 12:00 PM
I read a question that I quickly replied to, but I wanted to expand on my recommendation
#Ruby #Pattern #Return #CodeDesign
What I will share here is an exploration and a proposal about how I think we can improve it:
#Ruby #Pattern #Return #CodeDesign
What I will share here is an exploration and a proposal about how I think we can improve it: