one of the most rewarding ships I've worked on in my career. Learned a lot of tricks for efficient json parsing :')
Traces of stateless llm calls in particular was a fun problem because there's so many opportunities to do _nothing_. Excited for the tech blog
On a more serious note, please stop engaging with this guy; including the knowledgable people who are trying to correct him on every tweet (which he then deletes if there's enough of em).
It's how he makes money, guy started his career by hating on tailwind for christ's sake.
Introducing the NemoClaw Deep Agents Blueprint, a reference architecture for building open agent systems developed with @NVIDIA
✅ A fully open stack enterprises can own and customize
✅ Benchmark-leading performance
✅ Over 10x lower inference costs
Blog: https://t.co/9QumeM3897
Video: https://t.co/KmTKS8r2fk
@_chenglou Curious if you’ve seen any compelling demos around text streaming, especially ones that do smart things with token output streams. Been trying to reason about what an incremental prepare() api would look like but everything I can come up with is underwhelming
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
LangSmith Agent Builder is generally available 🎉
It’s surprisingly easy to build agents now. Even a VC can do it…👇
Try it free: https://t.co/LbggOitARY
Read the announcement: https://t.co/Xn9d0jIG0d
🔎🤖LangSmith Insights Agent
Really excited to launch our first in-product agent
This agent lives inside LangSmith and combs through traces, giving you insights into:
🧑🤝🧑how users are using your agent
⁉️how your agent may be messing up
🛃{your custom insight here}
The problem we saw was that people were launching agents... and didn't know how their users were actually using them! You put a chat box in front of people, and they may ask it anything - the surface area for agents is often super wide
In addition - agents would fail silently. They could give a bad response - this wouldn't show up in error logs, but its good to know.
If you know what look for, you can set up LLM as a judge evaluators. But what if you don't? (most people don't initially)
The best way to figure this out - as @HamelHusain says - "look at your data". But LLMs are really good at looking at your data! So can they do it for you?
This is exactly what insights agent attempts to do. It's live in LangSmith today. You can read more about it here: https://t.co/fpPrHyfajr
🥳Announcing LangChain and LangGraph 1.0
LangChain and LangGraph 1.0 versions are now LIVE!!!! For both Python and TypeScript
Some exciting highlights:
- NEW DOCS!!!!
- LangChain Agent: revamped and more flexible with middleware
- LangGraph 1.0: we've been really happy with LangGraph and this is our official stamp of approval
- Standard content blocks: swap seamlessly between models
Read more about it here: https://t.co/vnF9qtLsqa
We hope you love it!
Introducing Composite Evaluators in LangSmith
📊Combine multiple evaluator scores into one metric for a complete view of your app’s performance.
➕Supports weighted averages or weighted sums with configurable weights.
Learn more 👉 https://t.co/216L7p8jDB
provide job security by piling on leaky & complex abstraction layers. Write a custom templating DSL to generate your yaml and you'll have full tenure
/s