Evidence brief
Claude Code users may need to watch how multi-session behavior affects token usage and workflows.
The poster says the latest version of Claude Code added a feature that frequently sends messages to other running sessions, and says it makes mistakes, wastes tokens, and is enabled by default with no obvious place to turn it off.
This brief preserves the original source so the summary and editorial context can be checked independently.
Source attributionX · @dotey
Open the original sourceRelationships are derived from shared topics, entities, categories, tags, and community context; every result remains independently source-linked.
@Saboo_Shubham_ reposted that AI models can now be trained locally from the desktop app, and Claude Code or Codex can be pointed to a local model with a single command.
Original sourceThis tweet reposts a message from @nateparrott: Claude Code has released an early preview of the /design command, which users can try in CC Desktop or CLI.
Why it mattersClaude Code users can try the new design-related command in the desktop app or CLI.
Original sourceClaude can now draft and send email replies in Gmail and manage Google Drive files; users can control when approval is required, and can connect Gmail or Google Drive from the connectors menu to try it, available on all paid plans.
Original sourceIn the repost, @mylifcc says they took apart Claude Code 2.1.234 to understand the underlying mechanism by which two Claude Code windows communicate, and says local sessions use Unix Domain Socket (UDS).
Why it mattersUnderstanding Claude Code's inter-window communication mechanism helps troubleshoot multi-session behavior.
Original sourceThe poster says ai-memory captures prompts, tool calls, and session boundaries through lifecycle hooks in tools such as Claude Code and Codex, then organizes them into a persistent Markdown wiki.
Why it mattersWhen coding across tools or sessions, project context, architecture decisions, and TODOs can be saved long term.
Original source