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.
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.
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)
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.
The original creators of the early version of the Internet wanted it to be open and equal, making sure one entity couldn't control it. The fact that this design also would be helpful after a nuclear attack was used to get the required funding from the US military.
It probably exists, but not very well known, or is too expensive to use. For example, I wrote a SpamAssassin extension that adds some score to messages based on whether LLM thinks it is a spam email. It worsk very well, but it's a bit pricey when it comes to API costs. Maybe if I switch it from GPT3.5 to Claude Haiku it will make more sense.
I think we still need to see prices of LLM tokens go significantly down and performance increase before such web filtering solutions make sense. The Claude Haiku is a big step int he right direction, but the price is still high for this kind of high-volume usage.
To those who suffer headaches after the aura, not many people realize there is an interesting trick. When you notice the first signs of your aura, try to close your eyes and either go to a dark room or cover your closed eyes with your hand (to make it as dark as possible). In many cases, this will result in a less visible aura and less intense headache.
I read about it on some obscure forum that I'm unable to find right now. Many people commented that it works for them. I tried it, and it definitely lowered the intensity of my ensuing headache. I used to use the time during and right after aura to do the most important things I had to do for the day before the headache took me out of commission for the next 6 hours. But now, on the first sign of aura, I try to close my eyes and go to a dark room. This makes my headaches much more bearable and shorter.
A few people claimed this allows them to stop the aura from spreading (it slowly fades for them as it moves and completely disappears before reaching the edge of their vision) and they don't have the headache at all. I wasn't able to do that, but it makes me wonder if the visual inputs coming from our eyes somehow intensify the wave that is spreading in our brains. And maybe closing our eyes and stopping the inputs from our eyes deprives it of some stimuli that it needs to progress?
A few months ago, I was able to witness my aura from the very beginning. I was trying to fall asleep, and I suddenly realized there was a very faint tiny dot a bit below the center of my vision. It looked like a dead pixel on an LCD screen, but super tiny. It was very faint, almost black, at first. But it quickly became brighter. I focused on it, and I noticed that it wasn't a solid dot. Instead, it looked like it had the shape of a rectangle that was sort of morphing into another rectangle that was rotated by 45 degrees. A bit like a wireframe of a rectangle, actually. Then, the bright rectangle started pulsating and changing rapidly between very bright white and a dimmed white. That's when I realized that it must be an aura starting. It then followed the usual pattern of getting bigger and slowly moving out of my vision.
It was quite fascinating to observe it from the very beginning. But now I freak out every time I see any kind of white dot in my vision when I close my eyes at night. And actually, when you really focus, you will realize that there are many tiny white dots and weird shapes popping out when you close your eyes at night. We just never pay attention to that, but the "idle" activity in our brain and nerves generates some artifacts when we close our eyes.
I have been looking for my trigger(s) for many years, and I still haven't found it. However, I definitely get more migraines when I experience periods of stress and/or sleep issues. Eating unhealthy snacks (candy, chocolate, etc) tends to increase the odds of me having a migraine.
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.