MullerGary

Web3/Rust Developer
Mfers
Core Developer of @Tokendance
Employee at @BytedanceTalk

[MullerGary @0xMuller]

MyShell Testnet ◤Phase 01◢ is Live!#MyShellTestnet Join the revolution and (open, AI) with me @myshell_ai: https://t.co/ZOiMsyG4yA

[MullerGary @0xMuller]

@VoidAsuka 在北京吃过最好吃的驴肉火烧

[Star@Day1Global Podcast @starzq]

市面上AI工具层出不穷，但每个工具基本上只能解决一个点，实际的工作流里面需要逐个调用， 非常费时间，且很难复用

@myshell_ai 近期上线了应用组件拼接能力，我搭了1个Bot, 1分钟把播客变成短视频，还获得了token奖励！

本🧵分3部分介���

1️⃣ 如何搭建复杂任务bot
2️⃣ 经济系统
3️⃣ 终极个人助手

👇

[MullerGary @0xMuller]

@pepemedicieth sure

[𝘁𝗮𝗿𝗲𝘀𝗸𝘆 @taresky]

《无风险年化 360%？小白也能懂的 Crypto 套利》

咱下午说的文章写好了，由于需要配图，试用了一下推特的文章功能。

也欢迎移步我的 Blog 查看 https://t.co/ipqLD3Qv72

如果觉得有收获，欢迎点赞转发一键三连。

[Element NFT Marketplace @Element_Market]

🔥Discover the latest #Giveaway on Element, presented in collaboration with our friend and #ELEDAO member @DeBox_Social.🦈

🎁150 * DeBox Guardians Shark WL
⏰Ends at Mar.12th 15:00 HKT
👉Participate now: https://t.co/GYW1LAcFIa
👉For EPG/EPS holders: https://t.co/L71kMclXOZ

#Giveaway #ELEDAO #Debox

[SimpDoge（ERC404）👅 @Simpdoge_me]

🚀 $Simp, the first #ERC404 Token on @arbitrum, has launched NFT!

🎁 There are 10,000 #SimpDoge 404 NFTs available, with each token representing a blind box.

🧵 Check out the details 👇

[MullerGary @0xMuller]

Verifying my Twitter account for my #GalxeID gid:LXNRmAW3d5ycQaBp48d6Qn @Galxe

https://t.co/MClGeM2ySt

[Alex Xu @alexxubyte]

How do we manage configurations in a system?

The diagram shows a comparison between traditional configuration management and IaC (Infrastructure as Code).

🔹 Configuration Management
The practice is designed to manage and provision IT infrastructure through systematic and repeatable processes. This is critical for ensuring that the system performs as intended.

Traditional configuration management focuses on maintaining the desired state of the system's configuration items, such as servers, network devices, and applications, after they have been provisioned.

It usually involves initial manual setup by DevOps. Changes are managed by step-by-step commands.

🔹 What is IaC?
IaC, on the hand, represents a shift in how infrastructure is provisioned and managed, treating infrastructure setup and changes as software development practices.

IaC automates the provisioning of infrastructure, starting and managing the system through code. It often uses a declarative approach, where the desired state of the infrastructure is described.

Tools like Terraform, AWS CloudFormation, Chef, and Puppet are used to define infrastructure in code files that are source controlled.

IaC represents an evolution towards automation, repeatability, and the application of software development practices to infrastructure management.

–
Subscribe to our weekly newsletter to get a Free System Design PDF (158 pages): https://t.co/uc5M7CdXXC

[Harrison Chase @hwchase17]

Lance (@RLanceMartin) has done a TON to bring advanced retrieval topics to @langchain and make them easily approachable and understandable

This image he put together for our "RAG from Scratch" YouTube series is absolutely 🔥

(YouTube: https://t.co/kq285rHcZz)

[LlamaIndex 🦙 @llama_index]

12 RAG Pain Points and Proposed Solutions 💡

Building production RAG is hard. @wenqi_glantz compiled a list of 12 (!!) RAG pain points + added a full solution list to each one with @llama_index abstractions 🔥

We’ve put out cheatsheets before, but this one is much more comprehensive. This is a must have mapping if you have pain points in any one of the following listed areas:
1. Context Missing in the Knowledge Base
2. Context Missing in the Initial Retrieval Pass
3. Context Missing After Reranking
4. Context Not Extracted
5. Output is in Wrong Format
6. Output has Incorrect Level of Specificity
7. Output is Incomplete
8. Ingestion Pipeline Can't Scale to Larger Data Volumes
9. Inability to QA Structured Data
10. Document (PDF) Parsing
11. Rate Limit Errors
12. LLM Security (prompt injection)

Check out the blog: https://t.co/sP12g5Hli0

This builds on the paper “Seven Failure Points When Engineering a Retrieval Augmented Generation System” by Barnett et al. (check it out here: https://t.co/670udFeewI).

[Alex Xu @alexxubyte]

Linux file system explained.

The Linux file system used to resemble an unorganized town where individuals constructed their houses wherever they pleased. However, in 1994, the Filesystem Hierarchy Standard (FHS) was introduced to bring order to the Linux file system.

By implementing a standard like the FHS, software can ensure a consistent layout across various Linux distributions. Nonetheless, not all Linux distributions strictly adhere to this standard. They often incorporate their own unique elements or cater to specific requirements.

To become proficient in this standard, you can begin by exploring. Utilize commands such as "cd" for navigation and "ls" for listing directory contents. Imagine the file system as a tree, starting from the root (/). With time, it will become second nature to you, transforming you into a skilled Linux administrator.

Have fun exploring!

Over to you: which directory did you use most frequently?

–
Subscribe to our weekly newsletter to get a Free System Design PDF (158 pages): https://t.co/uc5M7CdXXC

[beihuo @beihuo]

2023年，我最大的收益之一就是发现了许多优秀的书籍。这些书对我的职业发展提供了极大的帮助。照片中是我去年买的和职业发展相关的书籍。大致可以把这些书分为三个类别。

第一类，关于理解和成为（或选择不成为）Manager 的书籍：

- 《The Manager's Path》✨（经典必读，即使不想当 Manager）
-《An Elegant Puzzle: Systems of Engineering Management》
-《Become an Effective Software Engineering Manager》（读的 Kindle 版，里面有非常实用的技巧）

第二类，旨在帮助你成为更出色的工程师的书籍：

-《Staff Engineer: Leadership beyond the management track》✨
-《The Staff Engineer Path》

第三类，专注于培养更优秀的团队和工作环境的书籍：

-《Shape Up》✨
-《Rework》
-《Remote》
-《It doesn't have to be crazy at work》

在每个类别中，我特别标注了✨的书籍，意味着如果你只打算在该类别中选择一本书阅读，那么我推荐这本。

[Jerry Liu @jerryjliu0]

There was a lot of cool RAG research in the past year or two, and luckily for you, all of these efforts are tracked under one place!

“Retrieval-Augmented Generation for Large Language Models: A Survey” by Gao et al. does an admirable job categorizing all RAG research into three categories: 1) pre-trained models (e.g. RETRO), 2) Fine-tuning + RAG (e.g. RA-DIT), and 3) RAG in inference mode (e.g. DSP).

Within the last category (which @llama_index has predominantly focused on), the paper walks through all the different components.

Check the paper out! ttps://arxiv.org/abs/2312.10997

This paper inspired @_nerdai_’s fantastic blog post that we posted about: https://t.co/G1hAyRy1Jf

[Zhiqiang Shen @szq0214]

Key observation one: For improved responses, it’s not necessary to be overly polite with your LLM, and don't be too stingy. Consider 'tipping' your model for more informative outputs!😀

[MyShell.AI @myshell_ai]

🎉It’s so excited and honored to be part of Binance Incubation Program.

💪Let’s build the next generation web3-based generative AI community together！

[MyShell.AI @myshell_ai]

🤖️Discover your innovative AI friends！

🎁Win amazing Badges, Linea ETH rewards and so much more!

🥳Join us today and get ready for an unforgettable AI x Web3 life. Let the fun begin!

@LineaBuild #Myshell

https://t.co/meEtCZi1Ig

[MyShell.AI @myshell_ai]

The BEST translation tool EVER is here! 🤯

1️⃣ Four different tones to fit any translation scenario!
2️⃣ One-click copy with Markdown - so easy! 🖱️
👇 Check out this reference prompt, customizable for any target language!
Click this link to try it now:https://t.co/xsuA0PdulN

[MullerGary @0xMuller]

@gundrymd_ @DogeInMyShell how about it

[MullerGary @0xMuller]

@3web3io @DogeInMyShell