Our AI agents bootcamp starts tomorrow! 🚀 Learn how to build sophisticated agents that can tackle real-world challenges in just six short sessions.
On day 1,
@JohnGilhuly
and Dat Ngo will cover core concepts like components, execution branches, and routers. They'll also touch
NYC: Build better AI with us on Sept 26. 🗽
Connect with AI practitioners, gain insights from teams that have successfully deployed LLMs, and stay at the forefront of LLM tooling.
We teamed up with
@pinecone
and
@guardrails_ai
for an evening of insights, networking, and spicy
Excited to have contributed to this deep dive on creating and validating synthetic datasets for LLM evaluation.
Synthetic data helps us test models, simulate app behavior, and create golden datasets for experimentation. Dive in if you're working with LLMs!
If you've been hearing a lot of buzz around AI agents but are not sure what tools are available and which ones you should use,
@aparnadhinak
shares helpful insights based as a leader whose company recently implemented a complex agent-based system.
What does an AI agent look like today? 🤖
My newest post on
@TDataScience
dives into different modern agent architectures, the current benefits and problems each brings, and my own recommendations on addressing these issues.
Agents have come a long way in the past year, from
While static guards are great at filtering out predefined content like NSFW language, they can struggle when faced with sophisticated attacks. Here's how to implement 🏎️ dynamic guards 🏎️:
🤖🤝 Imagine if you had a team of top-performers, each with their own specialty, that could work collaboratively to solve big problems, 24/7.
@crewAIInc
gives you just that.
And now you can trace your CrewAI applications with Phoenix!
Check out this walkthrough to see how you
Next week we’re talking to Kyle O'Brien, Applied Scientist at
@Microsoft
about his paper: Composable Interventions for Language Models.
Join us live:
This paper has important implications for how we can keep expensively trained models up-to-date over