←back to thread

422 points simedw | 1 comments | | HN request time: 0.237s | source
Show context
qsort ◴[] No.44433579[source]
This is actually very cool. Not really replacing a browser, but it could enable an alternative way of browsing the web with a combination of deterministic search and prompts. It would probably work even better as a command line tool.

A natural next step could be doing things with multiple "tabs" at once, e.g: tab 1 contains news outlet A's coverage of a story, tab 2 has outlet B's coverage, tab 3 has Wikipedia; summarize and provide references. I guess the problem at that point is whether the underlying model can support this type of workflow, which doesn't really seem to be the case even with SOTA models.

replies(4): >>44433628 #>>44435758 #>>44436819 #>>44440998 #
hliyan ◴[] No.44440998[source]
For me, a natural next step would be to turn this into a service -- rather than doing it in the browser, this acts as a proxy, strips away all the crud and serves your browser clean text. No need to install a new browser, just point the browser to the URL via the service.

But if we do it, we have to admit something hilarious: we will soon be using AI to convert text provided by the website creator into elaborate web experiences, which end users will strip away before consuming it in a form very close to what the creator wrote down in the first place (this is already happening with beautifully worded emails that start with "I hope this email finds you well").

replies(1): >>44453335 #
1. npmipg ◴[] No.44453335[source]
working on this as we speak!