Nischalj10

great to hear that - let us know how it goes!

we think good tests should cover all of these

looks slick.

thanks! for now, it will control the chrome window and block regular use. however, you can use the same profile in a new window while jobber runs in another.

just obsessed with browser controlling agents. I saw a few friends fret over the job search process, maintaining excel, going through job portals every day and then filling out the same repetitive applications. so we built jobber.

we are also building an underlying framework that lets devs build custom browser controlling agents.

>Also, does it have any downside since we are giving away browser control to it?

LLMs can take autonomous actions on your behalf and be sometimes wrong for sure. but this does not have the downside of you entering your passwords and the LLM having access to it as it controls your existing browser session where most of the websites are already logged in.

missed this in the readme. you can edit that in the user preferences file - https://github.com/sentient-engineering/jobber/blob/main/job...

it can search & apply for jobs on any platform. we've tested it on linkedin & wellfound. it also works in cases where the actual application is on a separate company page. the agent starts controlling the newly opened application tab in those cases.

this is crazyyyy

why not sign in with google?

is there something that's oss alternative to suno ai? any research papers on how to make own model like this?

a primer - https://github.com/nilsherzig/LLocalSearch/issues/17

This looks super cool!

Elastic

Hey. Kudos on the launch. What makes getprops different from the likes of litellm/ portkey ai? More deeply, would like to understand what’s your right to win/ unique insight in this increasingly crowding market if you are pursuing this as a startup?

really cool concept. Is this only available in US?

Nothing biased about Twitter algorithm - it’s the same for both. They managed to orchestrate a better launch virality by getting a lot of big names to post about them simultaneously - which is independent of the Twitter algorithm.

what is the best way to fine-tune these models? any good resources would be very helpful. TIA /\

PS - I have a brief background in Machine Learning, more in development.

A good summary of the paper here - https://notes.aimodels.fyi/enabling-language-models-to-impli...

I have been researching a lot around open source contributions, especially around hacktoberfest. Wrote this post to express my thoughts on the overall OSS contribution ecosystem for newbies.

Yeah, once the traffic is large it does make sense to have own compute

Thanks! Looks promising from the outside. Will surely check out

this looks much like replicate. has anyone tried it(https://replicate.com/). How's the experience with cold start?

We have models that are crucial but do not require dedicated hosting. We are looking for an aws lambda type of service, but for a fine tuned llama2-13b. any suggestions? would try out Cloudflare AI too.

really cool.

I have always been wondering for an open-source protocol for 2FA. Some of my 2FAs are in Authy, some in G Authenticator. Shouldn't there be one identity that can fetch all your 2FA from across providers?

hey! did you get to try it out?

>Mostly to get around bad docs. I need to implement things using libraries, services, and APIs that aren't well documented, but the source code is public, and people have written code against them, and ChatGPT has read all of the things that I would read (and more) to get to the point where I can use it, so I just ask it. The 2021 knowledge limit is pretty annoying, since libraries change so often, but it's still very useful.

can you try this out and let me know your feedback? https://chat.collectivai.com

use it to contribute to open source. one of the biggest challenge for someone while contributing is to get a hang of a complex codebase with not-so-well maintained community supported docs. tons of abstractions for the sake of extensibility makes it even harder for someone new to navigate. have been building and using https://chat.collectivai.com to solve this pain and make open-source contributions easier, more accessible and faster.

got it. why not a cross platform framework like flutter and expose to a much larger android audience as well?

got it. went through both of the codebases. what you say is the case. thanks!

i already want to put this in some text to video AI and put out a rap battle on Youtube

is this ancillary to what [these guys](https://github.com/unifyai/ivy) are trying to do?