It would be great if Beeper supported RSS in and out. It would help encourage other messaging services to do the same, and all of a sudden we’d have lots of easy interop instead of lots of really iffy interop. If they want to do it, I’d help, for free. Just to help things flow better on the messaging web, because we reallllly need help there. #

Members of the WordPress community. Monday morning is a good time to check out WordPress News via FeedLand at wp.feedland.org. You can also subscribe to the list of feeds this site follows in your own feed reader, and if you have a WordPress news site, please post the URL here so we can send readers to your blog too. I think there are a lot of would-be bloggers out there that need a slight kick in the pants to get going. I’m happy to provide readers if you provide the ideas. There’s a lot of power in WordPress that no one knows about. Let’s help other users and developers find the good stuff. If you have questions or suggestions, here’s a new thread on GitHub. #

I say to Claude: btw, i would have been surprised if it was broken, that feature went in very quickly and i use it a fair amount. one of the two big pages in feedland is the Feed List page. here’s a screen shot. maybe you can figure out what everything does??

Example of a Feed LIst page in FeedLand.

Claude retorts

• Disclosure triangle — expands the row to show more about that feed (recent items, description, full URL).
• Blue checkbox (checked) — subscription state. Checked = you’re subscribed. Click to subscribe/unsubscribe.
• Row number — just positional, 1..14 for this result set.
• Feed title — clickable, opens the feed’s own page (the other “big page” you mentioned).
• Small tag icon next to the title — opens a categories editor for that subscription, lets you tag the feed into categories.
• When column — last update time, with adaptive granularity: minutes for very recent (“21 mins”, “26 mins”), day-of-week for the past few days (“Fri”, “Tue”, “Thu”), month+day after that (“Nov 22”, “Mar 29”), and presumably full date for old stuff.
• Ct column — subscriber count for the feed. Every row shows 2 because feedland.social is small. Worth noting: this is the same
• ct that the SQL we just touched uses for
• order by ct desc — the column visible in the UI is the sort key.
• Green circle “i” — info popup, probably feed metadata (URL, description, last build, maybe owner).

Claude is very very smart. And I guess I got the right answers. A lot of work went into the design

The only thing it didn’t guess correctly about is what the other “big page” is. It’s not the Feed Info page, it’s the news page, a timeline or river.

Done for the day, my last words to Claude were — FeedLand is an important product and we’re going to do right by it.

A while back I was asking Claude (privately) if we could have it monitoring the messages posted to an app I’m working on. I wanted it to save them in a certain way, have it watch for messages that begin with //claude and maybe act on them somehow. I mostly just wanted to see if I could create a pipe and what its limits would be.

I asked what the max frequency is and was told it was 1 minute, meaning it would start a thread running Claude that would initialize, and it would read the file, and if there were any new items, it would process them, and then it would shut down. Barely enough to be useful, where we live we like notification within a second, but I went ahead, at least it’ll be a thought-provoking demo.

So I wrote the software. Not much to it, a Node app that’s hooked up to FeedlandSocket, and when it sees a message from me, it appends it to a JSONL file that Claude is watching. At most one minute later it wakes up and sees the new stuff and acts on it.

So I’m right there, it’s all working, the JSONL file is being saved in a public place, and when I ask it to start listening to my JSONL messages I learn that the max frequency is one hour, rendering my work useless. This has happened before, btw.

I asked what about all the “agentic” stuff they hype so much, how do I do that?? I can’t?? What?? Somehow I have trouble believing they’re all telling such a big lie. I wonder if Claude understands its own architecture.

Dave: “What is all this hype about agentic stuff. Every time I try to do something I hit a wall like this.”

Claude: “The pitch is ‘agents that run on their own’; the reality you just hit is a one-hour floor on the only scheduling path the tooling actually exposes. That’s not agency, that’s a batch job with extra steps. The honest read: the cloud-side scheduler is built around long-running, infrequent tasks (digest emails, nightly reports) because each run spins up a fresh sandboxed session, which is expensive. Anything that wants to react quickly to a stream of incoming items — which is what your app actually is — doesn’t fit that model. A plain local cron on some server running every minute would do the job today and cost nothing.”

I edited Claude’s response so as not to not reveal code names for products. 😉

A silver lining — I had never heard of JSONL, but it sounds pretty useful, so if I can’t hook up to Claude realtime, now — I can start using JSONL, which I wll.

Comments, stories, suggestions — here.