cadence-

I’ve gotten pushback from customers on this point a few times, so I wrote up my reasoning and wanted to see how others think about it.

My argument is that giving this information to customers who need it is different from publishing it openly to the whole internet. I think many companies treat public subprocessor lists as a default best practice without thinking enough about the security tradeoff.

Would be useful to hear from people who have handled enterprise security reviews, privacy reviews, or trust-center decisions.

Anthropic did the same thing with their Haiku model when they released version 3.5. I hate it.

It's working now with the 0.1.0 for me. But I will let you know if I experience any issues once I get updated to 0.1.1.

Thanks, great job! I like it overall, but I noticed it has some issues entering text in forms, even on google.com. It's able to find a workaround and insert the searched text in the URL, but it would be nice if the entry into forms worked well for UI testing.

How does this compare to Anthropic's Computer Use?

I was able to make it work like this:

1. Kill your Claude Desktop app

2. Click "Connect" in the browser extension.

3. Quickly start your Calude Desktop app.

It will work 50% of the time - I guess the timing must be just right for it to work. Hopefully, the developers can improve this.

Now on to testing :)

Doesn't work on Windows:

2025-04-07T18:43:26.537Z [browsermcp] [info] Initializing server... 2025-04-07T18:43:26.603Z [browsermcp] [info] Server started and connected successfully 2025-04-07T18:43:26.610Z [browsermcp] [info] Message from client: {"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"claude-ai","version":"0.1.0"}},"jsonrpc":"2.0","id":0} node:internal/errors:983 const err = new Error(message); ^

Error: Command failed: FOR /F "tokens=5" %a in ('netstat -ano ^| findstr :9009') do taskkill /F /PID %a at genericNodeError (node:internal/errors:983:15) at wrappedFn (node:internal/errors:537:14) at checkExecSyncError (node:child_process:882:11) at execSync (node:child_process:954:15)

Yeah, it's down. Musk should stop working remotely and get back to the office to fix it ASAP!

Does the Cursor have text-to-speech functionality?

It's a custom-built Slack bot that uses our KB articles, and previous customer tickets, to formulate responses and find links to relevant data. Our Customer Service staff uses those generated responses to write actual replies to customers. We currently don't have plans to let the system respond to customer queries directly.

It might not always be possible to directly translate it to revenue, but in my company, we started using an RAG system to help the Customer Support team answer inquiries. It replaced the old Knowledge Base articles search system, and it improved the number of processed inquiries by about 30%. This decreased customer support times and probably helped make customers happier, which is a pretty nice win, even if it would be pretty much impossible to attribute any revenue numbers directly to it.

It's nice to see that the hype is cooling. There will be more room to focus discussions on what's actually useful, and stop with the endless "I love it", vs. "I hate it", vs. "I fear it" discussions.

This looks pretty amazing. I will take it for a spin next week. I want to make a RAG that will answer questions related to my new car. The manual is huge and it is often hard to find answers in it, so I think this will be a big help to owners of the same car. I think your library can help me chunk that huge PDF easily.