【試聽】XEP22 - 兩篇最新 AI 研究分享:如何讓 LLM 處理超過1000萬個 token?透過重複 Prompt 來輕鬆提升 AI 回答品質?
About this episode
訂閲【科技浪 Pro】收聽本集完整版:https://open.firstory.me/join/techwav
Apple Podcast ”訂閲“與收聽專屬集數教學:https://youtube.com/shorts/UInyH51Pcs0?si=QLw3rTjOv5FUSlqs
Apple Podcast “已訂閲“收聽專屬集數教學:https://youtube.com/shorts/7LyIOhgJGOw?si=DuQvwuoVagTcuKXV
訂閲有問題請來信:[email protected]
本集筆記與精修逐字稿:https://open.firstory.me/user/techwav/posts/xep22-rgdnmbewn3n2
---
00:00 新年快樂!
03:34 兩篇論文
06:12 RLM是什麽
10:59 RLM的運作原理
14:07 RLM多强?
21:04 RLM的缺點
26:46 RLM怎麽用
31:53 論文二
---
商業合作:[email protected](請先參考:https://www.techwavpod.com/%E5%95%86%E6%A5%AD%E5%90%88%E4%BD%9C)
哈利的IG:harryspeaks_
Powered by Firstory Hosting
Get every episode summarized
Each time 科技浪 Tech.wav publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from 科技浪 Tech.wav
EP152 - OpenAI 自研晶片 Jalapeño 真的有點猛
科技浪 Tech.wav
【試聽】XEP28 - AI 時代創業的思考與學習:選題、護城河、商業模式、開發、銷售
科技浪 Tech.wav
EP151 - NVIDIA 的 CUDA 護城河消失中,但老黃已經想到下一步了?AI 輔助的個人化 mRNA 癌症療法來了!
科技浪 Tech.wav
EP150 - SpaceX 真的追上了!Google 危險了?Meta 重返開源|Bonus:哈利的氛圍學院正式上線!
科技浪 Tech.wav