[moffkalast]

What's the official take on the system prompt? The technical report doesn't mention it, but the official QAT GGUFs include some form of prepending it to the first user message. Has it been trained with any <start_of_turn>system turns with tool calls and such?

[alekandreev]

We recommend using <start_of_turn>user for the system prompt as well.

[tucnak]

I was under the impression that the purpose of "system" prompt is to encode the instruction boundary explicitly to reduce the risk of injection. Do you enforce some kind of security invariant that we could rely on? For example, does the alignment regiment include adversarial demonstrations so that out-of-order instruction-following (such as contradicting preceding) is penalised?