跳到正文
𝕏 a16z(x.com)·· 5 天前品質評分39
重點導讀

研究品味,是看出哪些點子長遠來說重要、能被其他想法接著使用,最後也可能超越最初發表的論文。

  • John Schulman 認為,研究直覺來自親自做研究,也要大量閱讀過去的成果,從中吸收經驗。
  • Mark Chen 則說,現在的模型還不太會想出好點子,反而更擅長調整超引數等細節。
  • 未來公司可能用人類回饋強化學習,請研究人員評分哪些想法好、哪些不好,讓模型從中學習。
  • 這很重要,因為做研究不只要把引數調好,還得知道哪些問題值得花時間。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

a16z
a16z@a16z
·5 天前
𝕏

John Schulman and Mark Chen on what research taste is, and how models might learn it:

John: "Research taste is about knowing which ideas are important in the long run, which ideas really catch on and end up going beyond whatever paper they first appear in, but being general and being composable with other ideas."

Mark: "There's taste, which is how you come up with the idea in the first place. The models are still not phenomenally good at taste. They go very deep into things like hyperparameter optimization, essentially tuning all the little knobs that you can tune."

John: "A lot of intuition just comes from personal experience doing research, but to get good at a certain research field, you also have to read a lot of the past work in that field, and you try to absorb the lessons from all this historical work."

"Companies will probably also just do RL from human feedback to collect data from researchers on which proposed ideas are good and which aren't. And that's kind of like absorbing whatever human intuitions the human researchers have developed and trying to bake that into the models."

@johnschulman2 @markchen90 @sarahdingwang

推文來源 · X (Twitter)在 X 參與討論
來源: a16z (x.com)
在 X 查看推文

讀者討論

理性交流 · 即時討論