1.5M ratings
277k ratings

From 2025

  • 可以戒 FB 了。
  • 專注極度重要的事。

2025年初

  • 放棄追求完美，能夠接受拼裝車的存在。
  • 不再想要嘗試說服或教育他人。時間有限，有更重要的事情要做。
  • 接受錢是熨斗，能把生活的一切皺褶熨平。
  • 減法原則的威力；包括生活，社交，專業領域。少就是多。
  • 願意無視也願意承擔。
  • 時間永遠不夠，只能快速飛掠。
  • 認識亖。

架構

  • Top-down and bottom-up, spec and tdd. 

流

  • 沉浸

飛

  • 新境界
  • 擴展

放

  • 一切都是最好的安排
  • 雲淡風輕
  • 隨遇而安
  • 向前看

無意間聽到這首歌 熟悉的旋律
以為是很久以前

查一下才發現是1999
也並非是頂久

《那麼愛你為什麼》
黃品源＋莫文蔚

-

最近小追一部串流
很接地氣

x.com

Reflexive AI usage is now a baseline expectation at Shopify

We are entering a time where more merchants and entrepreneurs could be created than any other in history. We often talk about bringing down the complexity curve to allow more people to choose this as a career. Each step along the entrepreneurial path is rife with decisions requiring skill, judgement and knowledge. Having AI alongside the journey and increasingly doing not just the consultation, but also doing the work for our merchants is a mindblowing step function change here.
en.wikipedia.org

Flow (psychology) - Wikipedia

+

“‘It was like floating,’ 'I was carried on by the flow.’”

… suddenly I realised that I was no longer driving the car consciously. I was driving it by a kind of instinct, only I was in a different dimension. It was like I was in a tunnel.

This study further emphasized that flow is a state of effortless attention. In spite of the effortless attention and overall relaxation of the body, the performance of the pianist during the flow state improved.

…flow is associated with achievement…

−

…enjoyable activities that produce flow have a potentially negative effect: while they are capable of improving the quality of existence by creating order in the mind, they can become addictive, at which point the self becomes captive of a certain kind of order, and is then unwilling to cope with the ambiguities of life.

arxiv.org

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

We present Step-Back Prompting, a simple prompting technique that enables LLMs to do abstractions to derive high-level concepts and first principles from instances containing specific details. Using the concepts and principles to guide the reasoning steps, LLMs significantly improve their abilities in following a correct reasoning path towards the solution. We conduct experiments of Step-Back Prompting with PaLM-2L models and observe substantial performance gains on a wide range of challenging reasoning-intensive tasks including STEM, Knowledge QA, and Multi-Hop Reasoning. For instance, Step-Back Prompting improves PaLM-2L performance on MMLU Physics and Chemistry by 7% and 11%, TimeQA by 27%, and MuSiQue by 7%.

“The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise.”
— Edsger W. Dijkstra

arxiv.org

LongNet: Scaling Transformers to 1,000,000,000 Tokens

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To address this issue, we introduce LongNet, a Transformer variant that can scale sequence length to more than 1 billion tokens, without sacrificing the performance on shorter sequences. Specifically, we propose dilated attention, which expands the attentive field exponentially as the distance grows. LongNet has significant advantages: 1) it has a linear computation complexity and a logarithm dependency between any two tokens in a sequence; 2) it can be served as a distributed trainer for extremely long sequences; 3) its dilated attention is a drop-in replacement for standard attention, which can be seamlessly integrated with the existing Transformer-based optimization. Experiments results demonstrate that LongNet yields strong performance on both long-sequence modeling and general language tasks. Our work opens up new possibilities for modeling very long sequences, e.g., treating a whole corpus or even the entire Internet as a sequence.