Lars Grammel
@lgrammel.bsky.social
i recommend cursor. tried switching back to copilot at some point to give it another shot and switched back to cursor almost immediately.
May 19, 2025 at 4:35 PM
i recommend cursor. tried switching back to copilot at some point to give it another shot and switched back to cursor almost immediately.
is that with the new chattransport?
May 19, 2025 at 9:19 AM
is that with the new chattransport?
For agent to agent communication you have to set up something custom - focus for AI SDK 5 is to improve assistant to user messages in the UI
May 10, 2025 at 9:58 PM
For agent to agent communication you have to set up something custom - focus for AI SDK 5 is to improve assistant to user messages in the UI
It's important to distinguish UI messages from model messages.
Having a clear separation makes it easier to set up (application specific) persistence for your UI messages and additional context. It also helps putting prompt optimizations in place and improving results.
Having a clear separation makes it easier to set up (application specific) persistence for your UI messages and additional context. It also helps putting prompt optimizations in place and improving results.
May 10, 2025 at 4:52 PM
It's important to distinguish UI messages from model messages.
Having a clear separation makes it easier to set up (application specific) persistence for your UI messages and additional context. It also helps putting prompt optimizations in place and improving results.
Having a clear separation makes it easier to set up (application specific) persistence for your UI messages and additional context. It also helps putting prompt optimizations in place and improving results.
The model prompt is often e.g. enriched and compressed.
E.g. short-term memory compresses, long-term memory and RAG enriches, system messages add additional information. You could have different model message prompts depending on the context.
E.g. short-term memory compresses, long-term memory and RAG enriches, system messages add additional information. You could have different model message prompts depending on the context.
May 10, 2025 at 4:52 PM
The model prompt is often e.g. enriched and compressed.
E.g. short-term memory compresses, long-term memory and RAG enriches, system messages add additional information. You could have different model message prompts depending on the context.
E.g. short-term memory compresses, long-term memory and RAG enriches, system messages add additional information. You could have different model message prompts depending on the context.
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
May 10, 2025 at 4:52 PM
UI messages contain additional information such as custom app data and metadata. Tools calls might be omitted. etc.
You can improve agent quality (i.e. success within a certain number of steps) with better prompts, tools, and other scaffolding - but you always need to account for the runaway run problem by limiting steps somehow (e.g. using a budget like tokens, steps, or money spent)
April 29, 2025 at 11:22 AM
You can improve agent quality (i.e. success within a certain number of steps) with better prompts, tools, and other scaffolding - but you always need to account for the runaway run problem by limiting steps somehow (e.g. using a budget like tokens, steps, or money spent)
And it autocompletes:
March 26, 2025 at 5:49 PM
And it autocompletes: