I don't know why we need a term like "Async AI programming." this is literally what you would do if you were a Tech Lead directing a team of other developers. You define what you want and hand it to one of your devs.
This is just being a TL. the agent is an assistant or a member of the team. I don't know why we need to call it "Async AI programming", unless we want to shy away from or obscure the idea that the agent is actually performing the job a human used to perform.
> is that it assumes you already know what you want at the start, and, implicitly, that what you want actually makes some real sense.
My experience is different. I find that AI-powered coding agents drop the barriers to experimentation drastically, so that ... yes if I don't know what I Want, I can go try things very easily, and learn. Exploration just got soooo much cheaper. Now that may be a different interaction that what is described in this blog post. The exploration may be a precursor to what is happening in this blog post. But once I'm done exploring I can define the problem and ask for solutions.
If it's DOA you'd better tell everyone who is currently doing this, that they're not really doing this.
> even in Japan somebody could make some kind of battery ignited home-made shotgun and kill Shinzo Abe
ok let's try data instead of feels. Per Capita, what is the number of mass shootings per year in the USA, and in Japan. I did't know the answer but asked Gemini.
The most recent year for which there is data, apparently, is 2023, during which there were 604 mass shootings in the USA, and 1 in Japan. Given the respective population counts, the per-capita rate of mass shootings in the United States was about 225 times higher than in Japan.
Given that, are you confident that your observation that "one guy made a gun once in Japan" is a strong refutation of the idea that the US could reduce mass shootings by strengthening regulations?
It's not a prompt injection _in the MCP Server_. It's injection facilitated by the MCP server that pulls input from elsewhere, eg an email sent to your inbox, a webpage that the agent fetches, or in the comment on a pull request submitted to your repo. [1]