+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Prompts / System Prompts (https://www.datasculpting.ai/inference/forumdisplay.php?fid=62)
+--- Thread: system prompt habits that helped: what are you seeing? (/showthread.php?tid=306)
Pages:
1
2
Re: system prompt habits that helped: what are you seeing? - northgarden37 - 09-23-2026
I hit almost the same issue last night.
Re: system prompt habits that helped: what are you seeing? - promptspark58 - 09-23-2026
that fixed it for me too.
Re: system prompt habits that helped: what are you seeing? - mlxgarden - 09-23-2026
Quote:that fixed it for me too.
I'd approach it in a boring order. Before rebuilding anything, I'd test one clean baseline with Llama and compare from there. At this point the real bottleneck is my patience.
Re: system prompt habits that helped: what are you seeing? - thetafield - 09-26-2026
Maybe, but I had the opposite result. I get why that seems right, but on A6000 the bottleneck felt elsewhere. Not saying you're wrong, just that I wouldn't lock that in as the lesson yet.
Re: system prompt habits that helped: what are you seeing? - northgarden37 - 09-27-2026
Thanks, that helps. I don't think your conclusion is far off. The biggest change for me was simplifying the stack instead of adding one more optimization layer.
Re: system prompt habits that helped: what are you seeing? - thetaarch43 - 09-27-2026
My first guess would be this: Start by verifying the driver/runtime combo, then test with a smaller prompt, then look at long context.