Hacker Newsnew | past | comments | ask | show | jobs | submit | cadence-'s commentslogin

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


Pricing is a hard problem. Theoretically, if companies occasionally raise prices dramatically once something is useful, they sometimes can create early demand and more testers for future product releases. Ofc they have to be careful to avoid annoying regular users too much. When you sell the harm is limited to late users, but when you rent it is harder to figure out the optimal strategy.


How does this compare to Anthropic's Computer Use?


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)


Can you try again?

There was another comment that mentioned that there's an issue with port killing code on Windows: https://news.ycombinator.com/item?id=43614145

I just published a new version of the @browsermcp/mcp library (version 0.1.1) that handles the error better until I can investigate further so it should hopefully work now if you're using @browsermcp/mcp@latest.

FWIW, Claude Desktop currently has a bug where it tries to start the server twice, which is why the MCP server tries to kill the process from a previous invocation: https://github.com/modelcontextprotocol/servers/issues/812


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.


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 :)


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


He admitted today he is having "difficulties" running his businesses.


Does the Cursor have text-to-speech functionality?


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.


My experience says, soon there will be a reduction in the company of the customer support jobs, bringing the customer satisfaction on par to before aka lower, but with slightly more money in the shareholders' pockets.


is this custom built or are you using a third party system that integrates with Zendesk, Intercom etc?


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.


So a really knowledgeable, specific search engine without ads or a customer base.

I hope you don’t pay for that service, you could train and run it yourself in… a week?


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.


How many tokens is the manual?


if its more than the 2M that will fit in gemini context then I want to know what car it is.


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.


Based on other things they said in the last couple of months, it looks like GPT-4.5 is coming this summer, and then GPT-5 in the Fall.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: