Message threads are now in public beta on the Messages API.
The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
Parked with lessons! The journeys of life are endless, this one has come to an end for another one to begin. I believe in your destination. Thank you for sharing.
@cyberomin Parked with lessons! The journeys of life are endless, this one has come to an end for another one to begin. I believe in your destination. Thank you for sharing.
I predicted this a couple of days ago. Frontier model labs are going hard on the application layer. Does this mean we have peaked on model development? Or there’s a truce by the labs to slow down, hence the focus on applications.
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
@claudeai I predicted this a couple of days ago. Frontier model labs are going hard on the application layer. Does this mean we have peaked on model development? Or there’s a truce by the labs to slow down, hence the focus on applications.
The big labs used to focus mainly on frontier models, leaving the application layer largely to independent builders.
Now they seem to be slowing the pace of pure frontier model development and shifting more attention toward products and agents.
Meta has Muse, OpenAI has Dots, and I suspect Anthropic is working on a similar product.
The open source community gave us amazing AI agents like OpenClaw and Hermes Agent. With this shift, I wonder what will be left for builders if the same labs that develop the frontier models are now also competing directly at the application level.
@SamIndyer its that universal standard which could be onchain providing a clear audit trail for governments to regulate and confirm ethics are being upheld.
This is the moment for a large superpower to control AI
@0xSheetal I think we do comms standard at different levels already. For example from the engineering standpoint we have MCPs, then Google’s agent2agent protocol etc.
What’s left is the connection of these pieces into a universally accepted standard.
The big labs used to focus mainly on frontier models, leaving the application layer largely to independent builders.
Now they seem to be slowing the pace of pure frontier model development and shifting more attention toward products and agents.
Meta has Muse, OpenAI has Dots, and I suspect Anthropic is working on a similar product.
The open source community gave us amazing AI agents like OpenClaw and Hermes Agent. With this shift, I wonder what will be left for builders if the same labs that develop the frontier models are now also competing directly at the application level.
@asemota EV era is here, in a very short time from now thousands of traditional technicians will be out of jobs. We’re sitting on a landmine . Something needs to be done and fast.
When we finally kick the bucket, this life sef go kneel dahn confess say we chop am! We worked hard. We read hard. We exercised hard. We prayed hard. We baby-boyed hard. We want to be remembered for being full option! Any time God says it’s time, we will say “Thank you, Father!”