Jeremy Selier

Tip: Figure out your personal ceiling for running multiple agents in parallel. We need to accept that more agents running doesn't mean more of _you_ available. The narrative is still mostly about throughput and parallelism, but almost nobody's talking about what it actually costs the human in the loop. You're holding multiple problem contexts in your head at once, making judgment calls continuously, and absorbing the anxiety of not knowing what any one agent might be quietly getting wrong. That's a new kind of cognitive labor we don't have good language for yet. I've started treating long agentic sessions the way I'd treat deep focus work: time-boxed and tighter scopes per agent dramatically change how much mental overhead each thread carries. Finding your personal ceiling with these tools is itself a skill and most of us are going to learn it the hard way before we learn it intentionally.

Introducing the Codex app, one place to build with agents. We can’t wait to see what you build with it.

(1/2) Personal Intelligence just landed in AI Mode – unlocking a Google Search experience that really *gets* you. Starting with subscribers, if you opt in to connecting Search to apps like Gmail and Google Photos, you can get responses that are uniquely helpful and tailored to you. I’ve been testing this out a ton and I’m genuinely impressed at how intuitive it’s been. AI Mode is not just searching, it’s helping connect the dots across my interests and preferences. For eg: it found family activities that slot perfectly into my travel plans – and even uncovered items that match my specific style... (like nailing it with recommending new shoes! 👟)