Tuesday, November 18, 2025
“Our kids can't play and we will not be able to walk due to traffic”
Last week Bunny found a flyer on our door:
NOTICE OF PUBLIC HEARING
THE COMMUNITY APPEARANCE BOARDCity of Boca Raton, Florida hereby gives notice:
6:00 P.M. on November 18, 2025
Boca Raton Community Center–Annex Building
260 Crawford Boulevard…
A phased mater plan amendment and site plan approvals to authorize the following on a 77-acre site, generally located at XXXXXXXXXXXXXXXXXXXXXXXXXXXXXX, with approximately:
- 68,276 square feet [6,343 m2 —Editor] of office;
- 150,000 square feet [14,000 m2 —Editor] of retail;
- 130,133 square foot [12,000 m2 —Edtior] hotel (185 rooms);
- 781 residential units; and
- 2,729 parking space
…
That 77-acre site (which is nothing but dense tropical trees) is right behind Chez Boca (and 32 other homes). This is not new—it's been something that the City of Boca has been threatening us with for the better part of fifteen years. And then yesterday, again on our door, we found another flyer, with largely the same information but with “Please attend it is urgent” and “Our kids can't play and we will not be able to walk due to traffic” scrawled in the margins.
Well, how can I pass that up?
At 6:00 P.M I found myself sitting in the Boca Raton Community Center Annex Building with about 50 other people. As the meeting began, it became apparent that this will happen. Maybe not next year, but eventually. Also, this meeting was to approve the architecture and landscaping only! No mention of traffic or noise would be brokered, nor would questions during the presentation of the architectural and landscaping firm. Afterwards, yes. But not during.
During the presentation, it was mentioned that the development was based loosely upon Mizner Park, an upscale mix-zoning development near downtown Boca Raton. They were going for a similar mixed-zoning but not with the same architectual style as Mizner Park. The plans aren't as dense as they're zoned for, so it's not quite the 150,000 square feet of reatil mentioned, which is nice. And they aren't developing the entire 77-acres—there's a large section in the north-east that will be left largely alone for now.
But one of my bigger concerns going into the meeting was ingress and egress. There are four potential spots for this—the one to the north would be a nightmare as it would be between the I-95 exit and residential homes. The one to the south is better—it's near the I-95 exit but not right on top if it. The final two spots lead directly into our neighborhood, at both ends of the street I live on!
Turns out there are only two points of ingress and egress. The main one on the south, and the other one off the street I live on (at the south end) to only be used by emergency vehicles like fire and ambulances; it will be fenced off from any traffic (car or foot) otherwise.
We were also assured that there will be a 100 foot (30 m) buffer between homes along the easter edge and any development, with none of the trees removed in said buffer space (with the exception of invasive species, which will be replaced with native trees).
I'm not trilled with the prospect, but if the current plans are followed, it's not horrible; it could be a lot worse. I also thought of asking when this development was supposed to actually start only after the meeting, but given how long this has been threatened, I'm not expecting any ground breaking any time soon.
I hope.
“Thanks for calling that out. That was bad advice on my part.”
For reasons,
I noticed that ClaudeBot
(and I'd link to the information page for it,
but,
and this is my shocked face,
they forgot to include a proper link!)
was repeatedly requesting the same file over and over again—/sitemap.xml.
My bad!
I neglected to configure my web server to return “410 Gone” for that page.
I went to the main site of the bot and found a “call to sign up!” but sadly,
no obvious link to stopping their bot.
So I figured, I might as well try this LLM thing once more. The last last few times I tried, it didn't go well. Maybe third time's a charm?
Maybe?
- Sean
How do I stop your XXXXXXX webbot from crawling my website?
- Claude
Thinks hard for a few minutes.
I can help you block Anthropic's web crawler from accessing your website.
You'll want to add rules to your robots.txt file. Here's what to add:
User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: /
Put this in your
robots.txtfile at the root of your domain (e.g.,https://yourdomain.com/robots.txt). [Apparently Claude doesn't know that there's a domain set aside specifically for examples, namely,EXAMPLE.COM. Claude also doesn't realize thatyourdomain.comactually exists! Way to go, Claude! slow clap]The two user-agent strings cover Anthropic's crawlers:
- anthropic-ai - the main crawler identifier
- Claude-Web - an alternative identifier that may be used
If you want to block specific sections instead of your entire site, you can replace / with specific paths:
User-agent: anthropic-ai Disallow: /private/ Disallow: /admin/
The crawler should respect these rules within a reasonable timeframe after you update your
robots.txtfile.If you're still seeing crawling activity after adding these rules, or if you need immediate blocking, you could also block by IP address in your server configuration or firewall, though the specific IPs may change over time.
- Sean
Finds the page that describes Anthropic's web bots, not from a link on the Anthropic web site, but a normal web search.
What about Claude-User? ClaudeBot? Claude-SearchBot? Did you XXXXXXX forget those? Or did your overlords tell you to conveniently “forget” those as well?
- Claude
You're absolutely right - I should have given you the complete list. Here are all the Anthropic crawler user-agents you should block:
User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Claude-SearchBot Disallow: / User-agent: Claude-User Disallow: /
I didn't intentionally leave those out - I gave you an incomplete answer, which wasn't helpful when you're trying to actually block the crawlers. Thanks for calling that out.
If you want to be thorough, you could also add a blanket rule that catches any variations:
User-agent: *Claude* Disallow: / User-agent: *anthropic* Disallow: /
Though the specific user-agent blocking is more precise if you want to maintain control over what else can access your site.
- Sean
Are you XXXXXXX sure that's legal syntax? That doesn't look kosher to me. Again, are you trying to get around any bans?
- Claude
You're right to call that out - wildcards with asterisks like *Claude* are NOT valid robots.txt syntax. That was bad advice on my part.
The correct approach is to list each user-agent explicitly:
User-agent: anthropic-ai Disallow: / User-agent: Claude-Web Disallow: / User-agent: ClaudeBot Disallow: / User-agent: Claude-SearchBot Disallow: / User-agent: Claude-User Disallow: /
That's the proper syntax. Each User-agent directive needs to be spelled out exactly, and wildcards don't work in the User-agent field in standard robots.txt files.
I'm not trying to get around anything - I just gave you incorrect technical information, which is worse than useless when you're trying to actually implement this. My apologies for the confusion.
Oh wait! I know! I'm holding it wrong, and I'm using an LLM that is older than 20 minutes. My mistake. And before you say I should have asked politely, no. This is a computer! It's not human! Stop anthropomorphizing it!
And of course, at the bottom of the chat page, grey-on-slightly-darker-grey, is the text “Claude can make mistakes. Please double-check responses.”
How anybody finds this garbage useful is beyond me.
![[Self-portrait with a Christmas Tree] Oh Chrismtas Tree! My Christmas Tree! Rise up and hear the bells!](https://www.conman.org/people/spc/about/2025/1203.t.jpg "Oh Chrismtas Tree! My Christmas Tree! Rise up and hear the bells!")