For one, because it breaks the Unix philosophy of "doing one thing and doing that well".
In that vein, I do want Firefox to develop/allow/improve an interface so that machines, amongst which AI-MCPs, can drive my firefox. And do so safely, secure, contained, etc.
So that my AI agent can e.g. open a Firefox tab and do things there on my behalf. Without me being afraid it nukes all my bookmarks, and with me having confidence in safety nets so that some other tool or agent cannot just take over my gmail tab and start spamming under my account.
Point is: I really think Mozilla and Firefox have a role to play in the AI landscape that's shaping up. But yet another client to interact with chatbots is not that. Leave that to people building clients please: do one thing and do it well.
In fact, the web browser may be the best example of a program antithetical to the unix philosophy. It is a single program that does rendering, password management, video decoding, dev tools, notifications, extension systems, etc. Adding some new AI component is rather on-brand for browsers (whether a good decision or not).
I don't want my web browser to be a mediocre PDF reader. I want my good and perfected PDF reader to be a PDF reader. I don't want my web browser to be a Web development IDE. I want a specialised (version of) a browser with all the developer tools and one that lacks all these features is lighter, safer and simpler for browsing.
I don't want an FTP client in my web browser (I don't want one anywere lol). Firefox was extracted from Mozilla back in the days exactly because Mozilla had become a browser that was bloated and crammed full of features that were unpolished or just subpar.
Firefox saved Mozilla and fought back by being lean, fast, and terribly focused at doing one thing and doing talhat well.
I want a browser that's good and forever improving in letting me browse the web and run and use web-apps.
> I really think Mozilla and Firefox have a role to play in the AI landscape that's shaping up.
Chiming in here as a Mozillian focused on AI not specifically related to Firefox - I agree! Just a heads up that a separate public benefit corporation, Mozilla.ai, exists and is supporting a suite of commercially-licensed, open source, general AI dev and enablement tools. That includes mcpd, what we're calling "requirements.txt for MCP", meant to enable more trusted automated interfacing between machines.
A goal here is to support developers looking to build out AI-enabled systems that interact with each other and with the Internet, be that through a traditional browser or some other way.
> For one, because it breaks the Unix philosophy of "doing one thing and doing that well".
I think that browsers abandoned this well before Firefox (or indeed, Mozilla) existed. These days a browser is an everything platform—perhaps ai could mitigate some of this damage.
I want a browser with a simple set of command line options that would let me navigate to a page, save the page or some part of it, trigger any of the actions that I normally do with the menu or mouse. Then I would be able to script it without having to install huge unstable things like Playwright and similar.
For one, because it breaks the Unix philosophy of "doing one thing and doing that well".
In that vein, I do want Firefox to develop/allow/improve an interface so that machines, amongst which AI-MCPs, can drive my firefox. And do so safely, secure, contained, etc.
So that my AI agent can e.g. open a Firefox tab and do things there on my behalf. Without me being afraid it nukes all my bookmarks, and with me having confidence in safety nets so that some other tool or agent cannot just take over my gmail tab and start spamming under my account.
Point is: I really think Mozilla and Firefox have a role to play in the AI landscape that's shaping up. But yet another client to interact with chatbots is not that. Leave that to people building clients please: do one thing and do it well.