[2304.05128] Teaching Large Language Models to Self-Debug
6
公开标注数
6
参与人数
2026-07-24 09:17:26
首次 Whisper
本页的公开 Whisper
划选高亮2026-07-24 15:41:26
原文高亮摘录
“arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.”
Whisper 随想笔记
Sounds like a cool way for the community to pitch in.
划选高亮2026-07-24 12:38:26
原文高亮摘录
“generating the correct solution in one go becomes challenging”
Whisper 随想笔记
I wonder if this works when the bug is in the logic, not just syntax.
划选高亮2026-07-24 12:29:26
原文高亮摘录
“generating the correct solution in one go becomes challenging”
Whisper 随想笔记
It's so true, one-shot code gen is rough for real projects.
划选高亮2026-07-24 09:35:26
原文高亮摘录
“Large language models (LLMs) have achieved impressive performance on code generation.”
Whisper 随想笔记
I tried something similar and it didn't help much with my own projects.
划选高亮2026-07-24 09:26:26
原文高亮摘录
“Large language models (LLMs) have achieved impressive performance on code generation.”
Whisper 随想笔记
This rubber duck debugging idea is actually pretty clever.
划选高亮2026-07-24 09:17:26
原文高亮摘录
“Large language models (LLMs) have achieved impressive performance on code generation.”
Whisper 随想笔记
Impressive but I wonder if this works as well for non-code tasks.
分享本页 Whisper
短链接
https://domwhisper.com/s/1043fe46babe嵌入代码
<iframe src="https://domwhisper.com/embed/1043fe46babe" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>