Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Nxtscape – an open-source agentic browser

github.com

Post reply on HN
Print view View original

181–190 of 228 posts

Re: Show HN: Nxtscape – an open-source agentic browser

#182

Post by sunnybeetroot »

dvt wrote: post #104

Suffers from the same problem as all other AI "workflows"--no one wants to fucking chat with a computer (Brave sort-of does this, and it's god-awful). A chat interface should only be used as a fallback if the agent is too dumb to figure out what I want. A chat interface works for ChatGPT because most folks use it as a pseudo-search, but productivity tools are (broadly speaking) not generative, therefore shouldn't be…

Have you used Cursor or Claude Code or any others? I want to chat to a computer and get it to do my programming over writing the programming myself.

Re: Show HN: Nxtscape – an open-source agentic browser

#183

Post by Calwestjobs »

kevinsync wrote: post #114

IMO comments so far seem to be not seeing the forest for the trees -- I can imagine incredible value for myself in a browser that hooks into a local LLM, writes everything it sees to a local timestamped database (oversimplification), parses and summarizes everything you interact with (again, oversimplification -- this would be tunable and scriptable), exposes Puppeteer-like functionality that is both scriptable via c…

my forest is this - "new LLM-based native ad-blocker"... this forest is so big my brain hurts of even thinking about it. (sarcasm sorry)

Re: Show HN: Nxtscape – an open-source agentic browser

#185

Post by lukasego »

kevinsync wrote: post #114

IMO comments so far seem to be not seeing the forest for the trees -- I can imagine incredible value for myself in a browser that hooks into a local LLM, writes everything it sees to a local timestamped database (oversimplification), parses and summarizes everything you interact with (again, oversimplification -- this would be tunable and scriptable), exposes Puppeteer-like functionality that is both scriptable via c…

This is an amazing vision. I want my browser to remind me if I lose focus, and to analyze and show me what I've been doing so I can learn from myself. Self-reflection is powerful here.

Re: Show HN: Nxtscape – an open-source agentic browser

#186

Post by ajb »

8organicbits wrote: post #154
ajb wrote: post #128

I think there is big value in something that is on the side of the user, in particular in processing user-hostile material. Here are some concrete use cases: * Buying a sofa. You want to filter for sofas of a specific size, with certain features, marketing sites want to feed you a bunch of marketing slop for each sofa before giving you the details . This generalises to many domains. * You have a few friends who are s…

> Buying a sofa. You want to filter for sofas of a specific size, with certain features This jumped out to me as well. Even sites like Amazon lack per-item-cost sorting, which can be really helpful when buying in bulk. Historically we've seen people use scraping and data science to build sites like https://diskprices.com/ ; without using LLMs. If LLMs are useful for those types of tasks, perhaps we'll see a surge in…

Yeah definitely. Also a problem when buying by weight or length. Length will be especially challenging for an LLM, as it needs to pick the right dimension.

Re: Show HN: Nxtscape – an open-source agentic browser

#187

Post by lolinder »

felarof wrote: post #157
adamoshadjivas wrote: post #149

Earlier quoted context omitted.

this sounds LLM generated regardless, you did not answer OPs point, which is that any potentially malicious site can prompt inject you at any point, and trigger an MCP or any other action or whatever before you see them and stop them. The whole point of an AI browser is like self-driving car, being able to de-focus and let it do its thing. If i have to be nervous to watch if im getting hacked at any given second, the…

I see, definitely agree that more work is needed in figuring out the right UX here. Probably open a shadow browser with OAuth sessions of only a small subset of sites required for the task?

That would help, but who defines which sites are required for the task? If it's the LLM you haven't solved prompt injection because the LLM can be persuaded to open other sites that the user didn't intend.
Post reply on HN