Dario Amodei is right that safeguards need time to catch up with AI capabilities. But companies deploying agents face a related question: how much authority should they hand over?
When model output becomes real action, AI safety doesn’t stop at the model.
https://t.co/TsT1oTsW2e
Where does it says in Temporal documentation to use an action for every write and read. Now I know what you are trying to do, piggy back on the latest news and sell your stuff. Nice try!!!
I doubt you even care to learn about durable execution and how it could add value for agentic loops like thousands of Temporal users are successfully using it for building with AI in a responsible way.
Anyone who knows @AmplifyPartners won't be surprised that I don't have any photos or cheesy videos of the 3 of us from back then. So this picture (the creation of which is aptly powered by Temporal) will have to do...
@ceo_clickhouse Also looking forward to your pic in @CPFC jersey at your next All Hands if they win. Will send you mine in @FulhamFC jersey if they win.
@ceo_clickhouse You’re on @ceo_clickhouse!!! Palace wins: $2K to Seattle Children’s Hospital. Fulham wins: $2K to the charity of your choice. What’s your pick? May the best infrastructure-sponsored club win. 🦅
@ShrivuShankar great to see Temporal adding value. Engineers building state management, retries, DLQ, etc as agents become more distributed and takes action in real world is not going to scale. It's so exciting to see @temporalio becoming the reliable foundation for AI systems.
Temporal’s LangGraph and LangSmith integrations are now in Public Preview.
If you’re building agents with LangGraph, you can now run them on Temporal without rewriting your codebase.
Keep the framework you already use and add the durability your agents need in production. All the details: https://t.co/Y5ieLKV2S8