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

Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

chrome.google.com

Post reply on HN
Print view View original

21–30 of 33 posts

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#21

Post by TheRoque »

I also wanted to do something like this. And I had other ideas for extensions using LLM to enhence the experience on the browser. Another one I wanted to do was a focus helper that notifies you (or block you ?) when you're not in a tab related to your work. You set a goal for your current session, e.g. "I'm currently working on my backend server", and the extension reacts on tabs unrelated to that (e.g. news websites or cat videos).

I think we're gonna be close to that, there's already models running in the browser (with https://webllm.mlc.ai/) the next step is to make it more efficient.

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#22

Post by poyu »

coolvision wrote: post #10
visarga wrote: post #6

Earlier quoted context omitted.

alway wonder why browsers don't keep at least a text version of the pages for search nowadays I expect browsers to incorporate small LLMs like Mistral out of the box

if history search worked better then you would visit google/bing less, so I expect pushback from browser vendors also: https://bugs.chromium.org/p/chromium/issues/detail?id=297648

Not every browser vendor runs a search engine…

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#23

Post by jondwillis »

apetresc wrote: post #2

Logical direction, but the real killer feature would be for an LLM to read every page you bookmark and not just categorize it once for you, but add it to a queryable knowledge-base that you can reference at any point in future conversations.

That gets real messy real fast!

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#24

Post by coolvision »

TheRoque wrote: post #21

I also wanted to do something like this. And I had other ideas for extensions using LLM to enhence the experience on the browser. Another one I wanted to do was a focus helper that notifies you (or block you ?) when you're not in a tab related to your work. You set a goal for your current session, e.g. "I'm currently working on my backend server", and the extension reacts on tabs unrelated to that (e.g. news websites…

hey we have similar ideas ) I made a focus helper thing as well: https://grgv.xyz/blog/awf/ webllm looks cool, but I would need to upgrade my laptop for it...

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#26

Post by coolvision »

bobjordan wrote: post #11

I had an issue with my bookmarks where I used chrome for about a decade and then one fateful day, I allowed Microsoft edge to try to clone my bookmarks. It corrupted everything. Now I have hundreds of copies of duplicated folders and links. It would be great if this or another tool could help get it restored.

the tool is called chatGPT ) just export your bookmarks to html, send to gpt-4, ask it to de-duplicate and organize, most likely it will work well.

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#27

Post by coolvision »

SunghoYahng wrote: post #14
SunghoYahng wrote: post #13

Thank you. I really needed it.

But is it possible to make this work for bookmarks (or better yet, links) that already exist? It will be great if it can.

would be nice yea, but that would need more work than MVP made over a weekend...

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#28

Post by smusamashah »

This is very helpful, exactly what I was looking for. I am using a custom local extension which submits bookmarks to https://dynalist.io/ and was thinking of integrating chatgpt with that somehow.

I haven't tried it yet but looking at screenshots, it will be nice if it supports importing and exporting bookmarks as plaintext. Even better a custom store for bookmarks.

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#29

Post by TheRoque »

coolvision wrote: post #24
TheRoque wrote: post #21

I also wanted to do something like this. And I had other ideas for extensions using LLM to enhence the experience on the browser. Another one I wanted to do was a focus helper that notifies you (or block you ?) when you're not in a tab related to your work. You set a goal for your current session, e.g. "I'm currently working on my backend server", and the extension reacts on tabs unrelated to that (e.g. news websites…

hey we have similar ideas ) I made a focus helper thing as well: https://grgv.xyz/blog/awf/ webllm looks cool, but I would need to upgrade my laptop for it...

Exactly what I had in mind, you nailed it. With some focus on improving the UI (a list of premade prompts, or a simpler way to make them) it could become widely used. Also, I think using the OpenAI backend is a huge blocked. I wonder how a small quantized model running in the browser would perform. Sad thing is that for now WebGPU is not running on Linux' browsers. Maybe CPU inference is enough.

Re: Show HN: Autolicious – AI-powered bookmark cataloging Chrome extension

#30

Post by coolvision »

TheRoque wrote: post #29
coolvision wrote: post #24

Earlier quoted context omitted.

hey we have similar ideas ) I made a focus helper thing as well: https://grgv.xyz/blog/awf/ webllm looks cool, but I would need to upgrade my laptop for it...

Exactly what I had in mind, you nailed it. With some focus on improving the UI (a list of premade prompts, or a simpler way to make them) it could become widely used. Also, I think using the OpenAI backend is a huge blocked. I wonder how a small quantized model running in the browser would perform. Sad thing is that for now WebGPU is not running on Linux' browsers. Maybe CPU inference is enough.

unfortunately only gpt-4 worked well in my experience, smaller models would work well only for blocking simple things like "cat videos page", but not for anything else less trivial. I have another proof-of-concept where smaller model fails compared to gpt-4: https://grgv.xyz/blog/apc/
Post reply on HN