GeekPlux Lab
344 subscribers
10 photos
1 video
2 files
1.6K links
随便发发,读了的,看到的,所思所想的。

闲聊:https://t.me/+F2FGJ9lGt3VhYTU9
频道主 blog: https://geekplux.com/
私聊 https://t.me/geekplux
Download Telegram
老头环美如画,我至今在老头环上玩的时间已经超过 400 小时,有时候就是进去逛逛都身心舒畅。尽管玩了这么久还是手残党,尽管老是被 boss 虐待,还是很喜欢这款游戏。 #游戏 #艾尔登法环

https://www.youtube.com/watch?v=a4XWVqXhBRI
Forwarded from Parallel Experiments (Linghao Zhang)
Naming is extremely important in Computer Science and, frankly, everything. Good naming is hard. Being able to pick a good name shows a lot of good taste.

Context engineering (a term promoted by Karpathy: https://vxtwitter.com/karpathy/status/1937902205765607626) is much better than:
- Prompt engineering: "Prompt" is just too overloaded.
- In-context learning: This is more of a research term and feels awkward to describe engineering required for building good LLM applications.
- RAG: Today, when done right, RAG is a very specific kind of context engineering. But too many people conflate it with "anything that puts stuff in the prompt".

Image credit: https://github.com/humanlayer/12-factor-agents/blob/main/content/factor-03-own-your-context-window.md
笔记还是要做的,但特别详细的笔记已经完全没必要了。而且我最近回归了用手写笔记,我发现现在笔记的要点在于激发创造力、激发灵感、串联想法。对于这些,纸和笔是最好的工具,有时候列几个关键字,画点结构图,勾勾划划之间就把事情想通了。打字笔记显得无效又笨拙,排版的过程更是对注意力的消耗。
#笔记 #notetaking
https://www.joanwestenberg.com/p/i-deleted-my-second-brain
👍1
非常 impressive 的跑步数据可视化。我至今觉得数据可视化,占很大比重的是设计,不是实现

https://nodaysoff.run/
👍1
DHH 最近和 Lex Fridman 的采访我也听了大概 40 分钟了,真的非常有趣,一来就提到 DHH 小时候打印再手输游戏的代码,就为了能免费玩游戏,然后最后卖游戏代码。他那时候不懂变量,看来变量赋值真的是一个编程入门的门槛。

6 小时真的太长了,希望能在接下来的几天中听完。

https://world.hey.com/dhh/the-6-hours-of-lex-888cbf16
老黄现场实录:“我当过全世界最没价值的CEO,也当过最有价值的”

https://mp.weixin.qq.com/s/8QnaqYsyGp_19hV4HXegEw