42-speaks-dev
Principles: share context & actions carry implicit decisions. Basically the advice is kind of like keep it simple stupid, claude code compacting, claude code multi agents only being used for researching and reporting back. only alpha is have a special purpose context compression LLM but even then they didn’t give too much info on the how
During execution, it's crucial for the agents to gain “ground truth” from the environment at each step (such as tool call results or code execution) to assess its progress.
Barry Zhang • Building Effective AI Agents
orchestrator workflow… rip milo
The reason the await call is needed in copyScore(from:) is central to the reasons actors are needed at all.
You see, rather than just letting us poke around in an actor’s mutable state, Swift silently translates that request into what is effectively a message that goes into the actor’s message inbox: “please let me know your score as soon as you... See more
You see, rather than just letting us poke around in an actor’s mutable state, Swift silently translates that request into what is effectively a message that goes into the actor’s message inbox: “please let me know your score as soon as you... See more
What is an actor and why does Swift have them? - a free Swift Concurrency by Example tutorial
Giving Claude a role with a system prompt - Anthropic
docs.anthropic.comIntroducing gpt-realtime and Realtime API updates for production voice agents
openai.com
OpenAI API: Responses vs. Chat Completions
simonwillison.netA Progressive Web App is a website; all its assets are the same as on the web, but with new tools to make those assets load fast when online and available when offline.
Welcome to Learn Progressive Web Apps! | web.dev
This workflow is particularly effective when we have clear evaluation criteria, and when iterative refinement provides measurable value. The two signs of good fit are, first, that LLM responses can be demonstrably improved when a human articulates their feedback; and second, that the LLM can provide such feedback. This is analogous to the iterative... See more
Barry Zhang • Building Effective AI Agents
hmmm this might be interesting if done right