Claude Code sessions can now message each other

#1 𝕏

Madhu Guru commented on Claude Code session-to-session messaging, using a figurative heist analogy to describe sessions communicating and operating without individual oversight.

#2 𝕏

Boris Cherny commented that the referenced harnesses support other models through proxies such as LiteLLM, but building an effective harness requires substantial model-specific tool design, prompting, and tuning.

#3 𝕏

Harrison Chase shared a 20-minute explanation of Managed Deep Agents, which he said had launched the previous day and combines a deep agents harness with managed LangSmith infrastructure. He also planned to film more tutorials over the weekend.

#4 𝕏

Harrison Chase shared Anthropic’s “Managed agents” engineering page, writing: “Separate brain from hands.”

#5 𝕏

Guillermo Rauch recapped Vercel’s cloud-bill protection functionality: soft and hard caps, anomaly alerting, recursion protection for Functions, agent-queryable billing usage APIs, and always-on L3/L4/L7 DDoS mitigation on all plans. Streaming data infrastructure supports this functionality, and Vercel analyzes ingested data in real time to detect anomalies and threats and dispatch alerts.

#6 𝕏

Peter Yang said excessive context, inadequate tools, and overly broad use cases are major obstacles to building great AI agents. He shared a picture of the product memo described as starting a production-agent project discussed by Nan and Jacob from Linear, while promoting a forthcoming full interview.

#7 𝕏

Sebastian Raschka shared a link to the rasbt/LLMs-from-scratch GitHub repository, noting that he should have shared the repository link.

#8 𝕏

Santiago said he had stopped reading AI-generated code and had not looked at any of it for two weeks, concluding that his time was better spent designing ways to verify the overall system. He said experienced human guidance is still needed, but checking every line is not, and argued that the IDE is on its way to the graveyard and new tools are needed.

#9 𝕏

Kevin Yien called point 4 on model voice “spot on,” arguing that people want AI to excel at needed tasks rather than sound human in uniquely human ways.

#10 𝕏

Boris Cherny asked whether Claude should automatically resume using Fable after a user’s limit resets or pause and let the user decide each time.