Hacker News new | ask | show | jobs
by Akhiljp 39 days ago
Ack on the guardrail analogy. On fireworks - do you just run serverless or do you take their dedicated instance. My question is how do you ensure that the model is not being manipulated to getting stuff it shouldn’t be.
1 comments
verdverm 39 days ago
"guardrail" is not an analogy, it is the term used in industry, you can search "ai guardrails" or "agent guardrails"
link
Akhiljp 39 days ago
My bad. Wasn’t aware. Thank you.

Looking forward to understanding the second part of this.

In fireworks - how does one build guardrails or it does not matter to companies hosting their models on fireworks?

link
verdverm 39 days ago
It doesn't matter where the models are, that's just a traditional API server. The agent harness is the thing that can read files and make http calls (to exfiltrate) and that's regular software running somewhere else. So one typically puts the harness in a sandbox and puts extra LLM calls in to guardrail (prompt / tool call checks).

I'm planning to do something like this for myself as an OpenCode plugin, but to stop my message and record it for clarity or block angry

link