[horizion2025]

Isn't that just another guardrail that can be bypassed much the same as the guard rails are currently quite easily bypassed? It is not easy to detect a prompt. Note some of the recent prompt injection attack where the injection was a base64 encoded string hidden deep within an otherwise accurate logfile. The LLM, while seeing the Jira ticket with attached trace , as part of the analysis decided to decode the b64 and was led a stray by the resulting prompt. Of course a hypothetical LLM could try and detect such prompts but it seems they would have to be as intelligent as the target LLM anyway and thereby subject to prompt injections too.

[wrs]

Yep.

https://gandalf.lakera.ai/baseline

[Huppie]

This is genius, thank you.

[dotancohen]

It took me days to complete!

[darepublic]

We need the severance code detector

[brianjking]

wearing my lumon pin today.