Coding agents | Tech
Tech news, context and sources.
Latest articles
Three coding agents collaborate through separate worktrees and shared contracts
Agreeing on data models and interfaces matters more than assigning tools by reputation.
The same Android app prompt produces different agent-generated results
A one-shot comparison highlights workflow and interface checks more than a general model ranking.
DeepSeek releases DSH, a research prototype for team coding coordination
The MIT-licensed prototype is not an official production product, and some planned features remain unimplemented.
TokenEconomizer targets repeated costs in coding-agent workflows
Repository knowledge, tool pruning and loop redirection produced benchmark savings, not universal guarantees.
Android Studio expands support for external AI coding agents
Agents can share IDE and emulator context, but release and experimental channels differ across tools.
GVS5H reports coding-benchmark gains from small-model coordination
Its shared-workspace results do not establish parity with current frontier models or with their performance on real software projects.
Corgi brings terminal sessions and coding agents into one workspace
It combines activity, token usage and file changes while keeping processes running after a session is detached.
Coding-harness study finds clearer cost gaps than success gains
Rerunning an unchanged setup helps distinguish small performance claims from measurement noise.
You’ve reached the end.