ត្រឡប់ទៅព័ត៌មានវិញ

AI · អត្ថបទ

Astra Adjusts Qwen's Weights So the Model Can Finish Its Reasoning to the End

Korben ·

មើលត្រួសៗ

MIT researchers asked OpenAI's model GPT-6 Astra to directly adjust the internal numbers of Qwen3.5-0.8B, a small AI model. By reducing the model's tendency to loop around the same point, the share of problems it finished solving rose sharply.

ចំណុចសំខាន់ៗ

ហេតុអ្វីវាសំខាន់

It shows that the problem of AI failing to reach a final answer may be solved by directly editing the model's internal workings.

ប្រភពដើម

Astra가 Qwen의 가중치를 손봐서 끝까지 생각을 마칠 수 있게 만들었어요

Korben · Nov 4, 13:44 KST

Read on Korben ↗

AI summarized the original article. Check the original for accuracy. Copyright belongs to Korben.

Qwen · ចំណាត់ថ្នាក់ និងព័ត៌មានបន្ថែម