Wanted to share my experience with @sh_reya @HamelHusain's It is the most in-depth, practical content on LLMs I've encountered. Lectures and exclusive book are 🔥. Essential if you're building AI applications.

Excited to be heading to Interrupt, LangChain’s AI Agent Conference, this week in San Francisco (May 13–14). If you’re attending, I’d love to connect in person. Feel free to send me a DM if you’d like to meet up during the event.

Overall, the course is an amazing opportunity to learn about the latest advancements in LLM agents. The lectures are not linear so you can cherry pick any that interest you. I highly recommend it.

Liang's call for greater openness and collaboration in AI research really resonated with me. It's crucial that we work together to understand and develop these powerful technologies responsibly.

@percyliang explored open-source and science in the era of foundation models (. He emphasized the importance of access to foundation models for research and discussed API access, open-weight access, and open-source access.

I was particularly fascinated by their discussion of web agents and the challenges they face, such as long context understanding and adaptability. It's clear there's still a lot of work to be done in this area.

@NicolasChapados and @AlexandreDrouin's talk introduced me to their TapeAgents framework and the WorkArena++ benchmark for Agentic workflows. (.

What really struck me was how Neubig emphasized the importance of human-in-the-loop systems for agents in software development. It's not just about automation, but about creating tools that empower developers.

@GrahamNeubig's talk on software dev agents ( was awesome. I learned about his OpenHands project and the challenges of building agents that can automate tasks to boost developer productivity.

The Berkeley LLM Agents course ( is an incredible free learning experience. All the lectures were top-notch, but three talks truly blew me away. 🧵. .

RT @readswithravi: but most importantly, just start.

EXIST then optimize.

RT @alexalbert__: Announcing the Build with Claude June 2024 contest. We're giving out $30k in Anthropic API credits. All you need to do i….

RT @willccbb: been learning a lot about LLMs etc over the past year, organized some of my favorite explainers into a “textbook-shaped” reso….

RT @chiefaioffice: New market maps covering the latest AI startups. 1. AI agents from Insight Partners

RT @yoheinakajima: AI Builders' Favorite Tools: A Hive Mind Survey Summary. I recently asked AI builders about their favorite go-to librari….

RT @rasbt: A suggestion for an effective 11-step LLM summer study plan:.1) Read* Chapters 1 and 2 on implementing the data loading pipeline….

RT @waitbutwhy: What, if anything, do you regularly use ChatGPT (or another LLM) for that has provided a dramatic improvement over your pre….

RT @infobeautiful: #Dataviz Books Everyone Should Read.

RT @hackohio: It's not too late to register for HackOHI/O 11! The registration deadline has been extended to October 25th! . Register NOW a….