I connected Claude to Firefox's ai pane and honestly I feel that this a good middle ground. I don't want an AI browser but I appreciate being able to have ai access specific pages when I have questions.
My only beef is they've basically put Claude's webpage on a side pane, with all the issues of a squished webpage.
I also think having a separate mode is really the best middle ground between an all spying ai-browser and one that has none (which makes doing some things with ai more manual)
> Claude's webpage on a side pane, with all the issues of a squished webpage.
I have used that feature for a few weeks now and find it utterly useless.
Partly because it is squished. But mostly because it offers no value over just having a tab open with Claude (or in my case Mistral).
The extra buttons (summarize) and integration (context menu) hardly ever work (pages and selections are often too large for gpt, copilot, mistral or even claude and the sidebar just gives an error) but even if they did: what problem do these extra buttons and integrations solve? Am I missing something?
Do note that I would love integration the other way around: to have an AI agent (through an MCP for example) drive my firefox. Safely, contained, etc etc. I am not an AI luddite. I just find the firefox sidebar offering no value at all.
And I think Firefox should step up and become a better alternative to playwright. One geared at developers with tools like profiling, dom-manipulation (basically the Developer Console) assertions, visual comparison etc.
Or (and?) one geared towards normal browsing and interacting with webapps.
I googled* it and dod the same. But that merely moves the problem forward. Now the API returns errors that it's too large.
A smarter client would use a tool chain in which the first step is a model that's good at taking large contexts/data and extracting actual content from it. Many sites have a very low S/N ratio (readable content / dom).
Then pass that content, eg markdown, along to a model that's optimized at getting relevant parts out of content for the task at hand.
And only then onto the generic model to "do stuff" with it.
But many clients, including afaiks the Firefox one, just send the entire dom or html along to a generic model.
Sorry for the late response; from what I can tell from my experience is that they're good at eliminating the unnecessary information (at least, as best as it can). You can see exactly what is passed in to the chat bot (for me, openweb-ui) and can see it's all text elements of what makes pertinent sense to be summarized.
My ideal would be an additional prompt that says "hey this page content is beyond your context length, fine with extending it to whatever the maximum context length plus some for the model's context length"?
I already do this via docker desktop MCPs in which I run a.o. Playwright¹.
Zed and VS code can now drive a browser. E.g. to perform tasks like "run the site on a local server and verify that you see the counter increase when you click this new plus-button"
I thought the AI pane was convenient. Then I wanted to try a different AI service, and couldn't do so without losing all the content in the currently open pane. And I realized - this would be so much better if it was just a regular tab. Like we already have.
My only beef is they've basically put Claude's webpage on a side pane, with all the issues of a squished webpage.
I also think having a separate mode is really the best middle ground between an all spying ai-browser and one that has none (which makes doing some things with ai more manual)