An agent is a model, a loop, and a set of tools. Where each of those runs determines what the agent costs, what it can do, and how safe it is to use: blog.exe.dev/topology
"When I want to improve one of my iOS apps, I shake my phone, type in a prompt, and off it goes to Shelley, with a screenshot." blog.exe.dev/shake-to-tell-s…
We're hosting our first technical meetup in SF on October 26. Drinks and pizza will be served, thrilling talks will be given. Join us: luma.com/0qr6bxcw
Sharing a CPU core comes with a security tradeoff. At exe, your team’s VMs can share cores with each other. Other teams’ VMs stay separate. And if your own VMs need that separation too, your team admin can turn sharing off. Ian explains how it works: blog.exe.dev/crossing-the-hy…
Lots of websites share an IP address. Somehow, you still get the one you asked for. Philip on the humble Host header, plus a new way to serve subdomains from a single exe VM: blog.exe.dev/the-hardest-wor…
ETOOMANYTHINGS: Running a bunch of agents at once to hide latency trashes your flow state. Here's what we're trying instead: blog.exe.dev/etoomanythings
Shelley can now take a screen recording as a prompt. Hit record, talk through your problem, click around, and your agent gets the transcript + video: blog.exe.dev/show-and-tell-s…
New lower pricing for the base @exedev individual plan: $15/month for 2 vCPUs / 4 GB memory. Instead of included tokens, link your ChatGPT subscription.
"My old mindset was wanting a bot to nag me into doing the thing. The new mindset is to have the bot take the task as close to the finish line as possible." blog.exe.dev/cron-vs-vm