Hi Groq team,
Have you seen this? Advancing LLM Reasoning: Deep Think with Confidence // DeepConf | by noailabs | Aug, 2025 | Medium
Would you be able to implement for your GPT OSS endpoints? It may greatly increase model performance and efficiency.
Thanks!
Do you know if there’s an associated white paper with more implementation details? I’d love to look into the paper and implementation! (but no promises on if we implement it in our stack though)
Maybe this could help?
interesting paper, thank you for sharing!