Claude Code's creator said something that stopped me cold:
"I don't prompt Claude anymore. I write loops — and the loops do the work. My job is to write loops."
Most developers are still crafting the perfect prompt.
The person who built the tool moved past prompting entirely.
In 30 minutes Boris reveals his actual daily Claude Code setup.
Claude Code + loops + dynamic workflows.
Worth more than any $500 vibe-coding course.
Watch it.
Then read this - everything you need to know about loops to actually apply what he says ↓
Bookmark both. This is your weekend.
Managing network access in AWS used to mean babysitting endless lists of VPC IDs. Painful. Easy to screw up.
Now AWS has 3 new condition keys that scale:
🔑 aws:VpceAccount → restrict to accounts
🔑 aws:VpceOrgPaths → restrict to OUs
🔑 aws:VpceOrgID → restrict to your org
💸SalesGPT: Elevating Sales Conversations with LangChain
SalesGPT is an awesome open-source repo that creates an AI-driven sales assistant
This blog by @andysingal deep dives into how this agent is created and how to use it
Blog: https://t.co/Va98j0pLxo
🎄LangChain 101: Embeddings and Vectorstores
Embeddings and Vectorstores are key to understanding RAG
Good community blog by Ivan Reznikov (3rd one in the series) explaining these concepts
https://t.co/so12lGwaBC
🗒️ LLMCompiler: blazing-fast agent execution 👾
🔀Plan tasks as a DAG.
🎏Stream parallelized task execution (while the planner is still thinking!)
🗣️Respond or replan.
Build it for yourself in LangGraph!
Python: https://t.co/a64pfF9FhT…
Youtube: https://t.co/fzzVNVFJcj
RAG From Scratch: Query Translation (Multi-Query)
Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code.
Over the next few days we'll release videos focused on Query Translation, starting with Multi-Query.
🔧 Problem: User queries are a challenge in RAG. If a user provides an ambiguous query, they can retrieve ambiguous documents w/ distance-based similarity search.
💡 Idea: Re-write the user question from multiple perspectives, retrieve documents for each re-written question, return the unique documents for all queries.
📽️ Video:
https://t.co/7aqRET7NKw
💻 Code:
https://t.co/DGogC0sEZc
🧠 Related works / ideas:
1/ Ma et al w/ RRR
https://t.co/LWzW7e5DVt
2/ @Raudaschl w/ RAG-Fusion
https://t.co/sQvYmcnHXb
3/ @RickLamers
https://t.co/VcNt24Q8xy
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)
New short course on LLMOps!
LLMOps (large language model operations) is a rapidly developing field that takes ideas from MLOps (machine learning operations) and specializes them to building and deploying LLM-based applications. In this course, taught by @googlecloud's Erwin Huizenga, you'll learn to use automation to make building, tuning and deploying an LLM-based application less manual and more efficient.
You'll learn how to:
- Apply supervised fine-tuning to tune an LLM to a specific task
- Automate and orchestrate LLM-tuning and deployment by customizing a pre-built tuning pipeline
- Apply best practices for preparing training data for supervised fine-tuning of an LLM
- Create an LLMOps workflow you can adapt to other LLM-tuning jobs
This course doesn't assume any prior MLOps or LLMOps experience. Sign up here to learn about this emerging field! https://t.co/UlDEbI0DbK
The @langchain team released 8 short videos so you can learn everything about the new v.0.1.0 version:
- Intro
- Observability
- Integrations
- Composability
- Streaming
- Output Parsing
- Retrieval
- Agents
https://t.co/RgCofTbGpq
📰🗞️Latest newsletter from @langchain is out and here are my 🔑take away in short:
Langchain Templates: Fastest & easiest way to get started building AI incorporated apps.
They can be your boilerplates to start building app with base code already available to you.
Hosted LangServe: Deploy apps easily using hosted version of Langserve soon. Sign Up for early access needed
7 Day of LangSmith: Great series of small videos explaining functionalities of Langsmith. Very informative and useful.
OpenGPTs: Open Source version of GPTs with better customization and local deployment.
Blog not to miss:
OpenAI’s Bet on a Cognitive Architecture - Explains about the future of cognitive architecture and why will it be important in future.
LangChain 🤝 Microsoft:
LangChain Expands Collaboration with Microsoft. This will be pivotal for Enterprise adoption. Soon available to on Azure Marketplace.
LangChain Core 0.1:
Langchain is stabilizing and becoming more robust to be incorporated in your production apps.
Let me know your thoughts on what you think about these great updates...
Links in the ALT
Giveaway! 🎉
I'm going to buy someone a new MacBook Pro M2 13".
To enter, retweet this tweet, then follow: @hakluke, @hacker_content & @haksecio.
If you're a cybersecurity org looking for high quality content and social media management, check out https://t.co/FfJsZ2HZYU 👇
Holy s**t. My @NorthSec_io workshop on #AzureAD tokens has been viewed almost nine HUNDRED times in a week 😳
Thank you so much for all the viewers 🙏For those who haven't seen that yet, the slide deck and link to the stream are available at https://t.co/3EcJMkfA64
Two weeks ago I had the chance to learn new recon techniques from the great @Jhaddix at #RSAC2023 and now I have more domains than I can handle. I built a tool to organize and sort the data called Recon MindMap. It's #opensource and it's available at https://t.co/PLZy39vTnL
The new Red Siege LOFI VOL II has dropped! https://t.co/al2Ri4een1
Set the vibe for the weekend!
The Red Siege LOFI VOL 2 is here for you!
Remember, if you are looking to make cybersecurity content, these tracks are 100% free to use.
#hacking#infosec#lofi