If you look at Elixir keynote for Phoenix.new -- a cool agentic coding tool -- you'll see some hints about a browser control using a API tool call. It's called "web" in the video.

Video: https://youtu.be/ojL_VHc4gLk?t=2132

More discussion: https://simonwillison.net/2025/Jun/23/phoenix-new/

Interesting project. I'm glad Vue is getting the same attention as the Svelte one. And props for digging in to optimize the payloads, and making it diff-able.

Can you just drop existing Vue components in there? Or are their LiveVue specific things you need to add?

Would love to read about some of the techniques for how you accomplished this.

> a consistent path to interacting with the world e.g sms, mail, weather, social, etc.

Here's an interesting toy-project where someone hooked up agents to calendars, weather, etc and made a little game interface for it. https://www.geoffreylitt.com/2025/04/12/how-i-made-a-useful-...

I would not want to read that every morning. Just show me the calendar and weather. The graphical representations are much faster to digest.

You may want to consider Elixir instead. It has an easier syntax and is (don't quote me on this) equivalent in function and purpose with Erlang. Plus you get lots of other goodies like LiveView (notebooks) and a good web stack (Phoenix).

I prefer Erlang because it makes the uniqueness of its paradigm clear. Tail recursion, function matching and, bang, everything is a message!

Elixir makes everything seem like Ruby code and many of those Erlang concepts are hidden away, which is also ok but also takes much away.

My aim with ErlangRED is that both are supported, there is a repository for Elixir code[1] that is included in ErlangRED - so I don't take sides, rather I would like to take advantage of both paradigms.

[1] https://github.com/gorenje/erlang-red-elixir-helpers

What a great timely tip. Was just looking for good direction on how to do this. Thanks!

For people wanting to dig into this idea some more, I'd recommend the book by Austin Kleon called "Steal Like An Artist." Also, there is some nuance in the book about copying and stealing, without being a thief.

If you want a better discussion about tariffs and their impact on the Boardgame Industry:

https://stonemaiergames.com/the-math-of-tariffs/

As others have said, avoid this article. It doesn't add anything meaningful to the discussion.

The two articles state different facts about the tariff situation:

- OP says 20% to 25% and states specific codes (and links to a government web site)

- the article to linked says 54% and contains no codes or links

Which one is correct?

> the article to linked says 54% and contains no codes or links

Correction: Jamie discusses “9504.90.6000” in the second-most recent comment below the post, likely as a response to this exact “no tariff codes, no knowledge” framing. (There could be other instances, I only skimmed briefly for it.)

Stonemaier games is the publisher of bestsellers like Wingspan and Scythe which have thousands of reviews on Amazon each vs TFA writer's game High Noon which has 8 review on Amazon. So I would trust that Stonemaier has more experience. Also when you type in the codes on the HTS website even the 9503 one the new tariffs aren't listed there or on any of the codes.

OK, glad I wasn't the only one who couldn't actually find the info the author said was on that site, using their link and the exact process they recommended.

To state the obvious (again), it's shocking the rate of progress is with these tools. If this is 2 years of progress, what does 10-20 look like?

Who knows, past progress doesn't predict future progress...

Totally agree. A general-purpose solution that ties together different messy interfaces will win in the long run -- i.e the IP protocol, copy-paste, browsers. In these cases, they provide a single-way for different aspects of computing to collaborate. As mentioned before, semantic web initiatives did not succeed and I think there's an important lesson there.