Anish Shah

Looking to go beyond basic LLM experiments and build real, production-grade applications? We have two free virtual courses designed for AI engineers of all levels who want to master RAG and LLM evaluations. Here’s what you’ll learn 🧵

@altryne Sad I missed this due to being at @COLM_conf but for large codebases it’s also nice to copy and paste files that you want as reference for the chat into a new folder and using (at)folder in the chat as opposed to (at)codebase (which adds a lot of junk context)

That's most of the insights, it was just fun to hand around and see how others use Cursor, what questions they had, discover uses together! 👏 What are your favorite things about Cursor that we didn't cover? Would love to hear and learn more 👇

We had a "Cursor tips & tricks" meeting today with my colleagues at @wandb and I figured I'd share what we 'discovered' & shared between us in a 🧵 If you haven't chatted with your team about how YOU all use Cursor, you def should, but meanwhile here are our insights 👇

🏆🏆🏆🏆 Four papers at COLM were awarded outstanding paper awards. Congratulations to the authors!

@gneubig @COLM_conf @allhands_ai @LTIatCMU Love the work at All Hands! Would love to chat if I can catch you around the conf

I'm looking forward to @COLM_conf in Philadelphia next week! Say hi to talk about research and/or positions at @allhands_ai and @LTIatCMU (It's also my first travel to a US conference by train 🚂)

The new @wandb RAG++ course uses the v2 API and the new command-r models. In addition to learning about nuanced RAG techniques, you also get to work with the new API in the course colabs thanks to the credits from @cohere. Register here: wandb.me/rag

📣 I am happy to announce that @wandb Weave is now integrated with Instructor (@jxnlco)! 🧶 Weave will automatically capture traces for Instructor. To start tracking, call `weave.init()` and use the library as normal. 👉 Learn more at weave-docs.wandb.ai/guides/integra…

Announcing our new RAG++ course, now available in collaboration with @CohereAI and @Weaviate_io. Created for engineers looking to build production-ready RAG systems. The course covers everything from evaluation strategies and data preprocessing to advanced retrieval techniques and prompt optimization and includes hands-on exercises with code notebooks and Cohere credits. Register here: wandb.courses/courses/rag-in…

Defining your grading criteria for LLM outputs is an organic process that evolves the more time you spend on it In “Who Validates the Validators” @sh_reya et al highlight this This weekend in our SF office a good chunk % of hackers will learn this 😃 lu.ma/judge

Today I gave @llama_index's workflows a go to tackle the NeurIPS AI hackercup competition. I created a Workflow to iterate from an initial solution, run the generated solution, and check against the expected output. It is effortless to define steps with the expected inputs and outputs. Define your Events and their attributes, and the workflow will be triggered in order when you hit run. I love how the @weights_biases Weave + step decorators play nice together. Try on colab: colab.research.google.com/github/wandb/a… Thanks to @LoganMarkewich for all the help! #hackercupai

I've been evaluating chunking mechanisms while prepping our RAG course's data ingestion lesson. Structured, semantic, and syntactic chunking each uniquely impact RAG performance. Learn to choose the right approach for your use case: wandb.me/rag-course

⚡️ AI Hacker Cup Lightning Comp Today we're kicking off a ⚡️ 7-day competition to solve all 5 of the 2023 practice Hacker Cup challenges with @MistralAI models Our current baseline is 2/5 with the starter RAG agent (with reflection) @MistralAI api access provided Details👇

Join us on September 10 to learn how to build production-ready RAG systems. Learn from @ash0ts about optimizing pipelines, enhancing queries, and scaling solutions for real-world applications. Ideal for tech leads and product managers driving AI innovation. Register now: wandb.ai/site/resources…

Join me tomorrow. I'm presentimg a codegen agent featuring RAG-based episodic memory and reflexion. Whether you're aiming to enhance your LLM toolkit or just curious about the latest techniques, this talk will deliver essential insights. 🔗events.bizzabo.com/NeurIPShackerc…

@capetorch pyenv uv 🤫

Lots of controversy about Anaconda charging their users these days. For most ML users, you probably use this on a CLI, and Miniforge is more than enough (actually better in many cases). github.com/conda-forge/mi… - Mamba is the default now - I actually have a simple setup script:

Stoked to partner with the team to host 7 lectures, a lot of agents creativity needed 📺 wandb.me/hackercup NeurIPS Meta Hacker Cup AI track gonna be 🔥

@GroqInc @e2b_dev @wandb Bonus tips for avoiding AI code hallucinations: Curate your datasets carefully! Garbage in, garbage out. 🗑️ Watch out for those pesky imports in the outputs! Don't forget unit testing & code reviews in your prompting! ✅

Key takeaways from the @GroqInc webinar: Iteration is key: Groq's speed lets you experiment with prompts super quickly! Sandbox your code: Use @e2b_dev 's secure environments to test without risking production systems. 🧪 Track everything with @weights_biases Weave = figure out what works best and why. 📊

Had a super insightful webinar with @GroqInc on debugging AI-generated code! Their inference speed with Llama 3.1 is mind-blowing, making trial and error so much smoother. youtube.com/watch?v=B70jJY…

I will be talking tomorrow on- - LLM landscape - Need for structured output - function calling, json, constrained decoding, more - RAG - LLM system evaluation - @wandb Weave for building LLM applications correctly If it excites you, consider showing up. 💫⭐🌟

Hallucinations in AI-assisted coding are a significant challenge for developers. Join Daniel Loman from @GroqInc and @ash0ts from Weights & Biases as they share strategies to overcome this issue in our technical webinar on August 6. Register now: streamyard.com/watch/hikcAgep…