The agents writing their own smoke-tests is the first habit that actually makes me trust the output more haha.
AUTOMATION
-
Eager for GPT-5.6 to play The Sims without a harness
By
–
Really looking forward to GPT-5.6. Playing a simulation of The Sims without any restrictions, it's completely insane.
-
AI codes all projects for 6-12 months, developer stops writing code
By
–
I have nothing to pump, I just let AI code all my projects for the last 6-12 months and don't write my own code anymore
-
Codex orchestrates thread handoff between local and remote hosts
By
–
https://t.co/VYkIRfhSha pic.twitter.com/v1EDg3XB0o
— CHOI (@arrakis_ai) 20 juin 2026Codex can now hand off threads between local and remote hosts. Start work on your laptop, send it to a remote box before you close the lid, bring it back later. And yes, Codex can orchestrate the handoff for you.
-
AI agent called 9000+ French bakeries to track baguette price
By
–
Brilliant to come across this right before @Cannes_Lions
: Someone had an AI agent call 9,000+ bakeries across France to track the price of a baguette. -
Quick patch adds rename to claude-channel-cli for role targeting
By
–
quick patch to `claude-channel-cli` in 0.3.0: you can now `rename` an instance to make it easier to target means you can have distinct roles (`project-reviewer`, `project-implementer`) and codex can route to the right ones. or they can even call each other with tasks
-
Claude message replaces SQL for trivial text edits
By
–
Probably even better now that trivial edits to it are a message to Claude away versus having to write a SQL query to do equivalent of a one character/line insert/edit.
-
Convergence towards agentic AI and value of agent-usable products
By
–
It's interesting to observe several companies converging towards integrating agentic AI features into their products, while I find that the most important value comes from companies that make their product usable by AI agents (MCP, CLI,
-
AI missing critical details in complex manufacturing documents
By
–
Have you experienced AI missing critical details in your complex manufacturing documents?
-
Brain: Self-improving context graph for stateful Computer tasks
By
–
We're rolling out Brain: a self-improving context-graph of all your sessions, connectors, and files. Brain updates itself overnight with fresh context proactively, and feeds itself to every task on Computer, allowing Computer to be stateful and self-improving. Available to all x.com/perplexity_ai/…