The world of web browsers have not been spared by the trend of integrating LLM functionality. But there are fundamental issues with it and Vivaldi addresses them.
Edge is branding itself “The AI Browser”. Chrome has plans to embed LLMs for text input. Opera, the browser which was commandeered from the original Vivaldi team and turned into a crypto/VPN gimmick browser, is of course among the hardest leaning into the LLM trend.
Webpage authors use LLMs to generate extremely long articles, to make you scroll by ads for longer. You use LLMs in your browser to summarize those articles. The circle of life, or something.
I stumbled upon a website through DDG, and after a long intro, the main section supposedly where the thing I was searching for had “Sorry I can’t fulfill your request right now”. Basically a fully generated page to match my search with some parasitic seo tactics. The web be chaging. Front page of DDG.
I’d love a browser-embedded LLM that had access to the DOM.
“Highlight all passages that talk about yadda yadda. Remove all other content. Convert the dates to the ISO standard. Put them on a number line chart, labeled by blah.”
You are falling into a common trap. LLMs do not have understanding - asking it to do things like convert dates and put them on a number line may yield correct results sometimes, but since the LLM does not understand what it’s doing, it may “hallucinate” dates that look correct, but don’t actually align with the source.
Thank you for calling that out. I’m well aware, but appreciate your cautioning.
I’ve seen hallucinations from LLMs at home and at work (where I’ve literally had them transcribe dates like this). They’re still absolutely worth it for their ability to handle unstructured data and the speed of iteration you get – whether they “understand” the task or not.
I know to check my (its) work when it matters, and I can add guard rails and selectively make parts of the process more robust later if need be.
That’s actually fascinating to think about. Would be a fun project to mash something like Blazor Server and an LLM together and allow users to just kindly ask to rewrite the DOM in plain English.
Arc has an LLM that lets you replace your search functionality with search or ask, where if you type a question it tries to answer it based on the content on the page. Kinda close to what you’re talking about.
Arc is genuinely trying to use LLMs in their browser in interesting ways.
Hmm I don’t think it’s because of that feature, because it only runs when you explicitly ask it to translate a page for you. You should probably check your extensions, see if you have some redundant ones (a mistake people make is use multiple ad-blockers/anti-trackers, when just uBlock Origin + Firefox’s defaults are usually good enough).
Quick tool to summarize a page, proofread, or compare it to another source. Still needs a functioning human brain to separate the wheat from the chaff so to speak, but I could see a LLM (especially local) being useful in some ways.
I’m sure there are disabilities or unique use cases that could increase it’s usefulness, especially once they improve more.
Didn’t even think of it as a possibility. WTF would a browser need with LLM?
Edge is branding itself “The AI Browser”. Chrome has plans to embed LLMs for text input. Opera, the browser which was commandeered from the original Vivaldi team and turned into a crypto/VPN gimmick browser, is of course among the hardest leaning into the LLM trend.
Cheers DANNY BOOOOOOOYYY!
Webpage authors use LLMs to generate extremely long articles, to make you scroll by ads for longer. You use LLMs in your browser to summarize those articles. The circle of life, or something.
I stumbled upon a website through DDG, and after a long intro, the main section supposedly where the thing I was searching for had “Sorry I can’t fulfill your request right now”. Basically a fully generated page to match my search with some parasitic seo tactics. The web be chaging. Front page of DDG.
Reminds me of the amazon products titled: “I’m sorry but I cannot fulfill this request it goes against OpenAI use policy,”.
I think we’re way beyond the point of no return. The internet has been ruined for good.
I do this already. It’s great. Kagi has a browser plugin that does it.
The circle of death.
I’d love a browser-embedded LLM that had access to the DOM.
“Highlight all passages that talk about yadda yadda. Remove all other content. Convert the dates to the ISO standard. Put them on a number line chart, labeled by blah.”
That’d be great UX.
You are falling into a common trap. LLMs do not have understanding - asking it to do things like convert dates and put them on a number line may yield correct results sometimes, but since the LLM does not understand what it’s doing, it may “hallucinate” dates that look correct, but don’t actually align with the source.
Thank you for calling that out. I’m well aware, but appreciate your cautioning.
I’ve seen hallucinations from LLMs at home and at work (where I’ve literally had them transcribe dates like this). They’re still absolutely worth it for their ability to handle unstructured data and the speed of iteration you get – whether they “understand” the task or not.
I know to check my (its) work when it matters, and I can add guard rails and selectively make parts of the process more robust later if need be.
That’s actually fascinating to think about. Would be a fun project to mash something like Blazor Server and an LLM together and allow users to just kindly ask to rewrite the DOM in plain English.
Arc has an LLM that lets you replace your search functionality with search or ask, where if you type a question it tries to answer it based on the content on the page. Kinda close to what you’re talking about.
Arc is genuinely trying to use LLMs in their browser in interesting ways.
Local translation of text comes to mind.
Yup, Firefox has it: https://browser.mt/ (it’s now a native part of Firefox)
Hmm maybe this is why Firefox is so damn slow on my raspberry pi
Hmm I don’t think it’s because of that feature, because it only runs when you explicitly ask it to translate a page for you. You should probably check your extensions, see if you have some redundant ones (a mistake people make is use multiple ad-blockers/anti-trackers, when just uBlock Origin + Firefox’s defaults are usually good enough).
Firefox has that already (without using an LLM). But yeah, it’s still another way this could be implemented or possibly improved.
I was thinking more along the lines of communicating with a Klingon captain on a D7 Battlecruiser.
Vivaldi has had local translation for about half a year now. No need for LLM for this feature.
Quick tool to summarize a page, proofread, or compare it to another source. Still needs a functioning human brain to separate the wheat from the chaff so to speak, but I could see a LLM (especially local) being useful in some ways.
I’m sure there are disabilities or unique use cases that could increase it’s usefulness, especially once they improve more.