Hacker Newsnew | past | comments | ask | show | jobs | submit | nischalhp's commentslogin

Hello,

This is exactly why we put this together. This project runs on your laptop / desktop with no outside connectivity, apart from pulling the model to your local compute ecosystem.

There is no room for prompts injection, because this is running locally and you can see the prompts and even modify them as its an open source project before you run.


Hi, appreciate the response.

In your demo video at least it shows the message that "If a message is deleted wrongly, please go to your trash and recover it.".

That's not a great UX.

If your tool is geared towards supporting people with bulk actions but I cannot modify in any way bulk actions prior to them being executed that creates more grunt work for me, then sifting through what I have to remember were wrongly deleted emails...

Also when I see the button "Schedule new cleanup" it reads to me like a background task running?

Or would this pop up at the specified time and prompt me for manual approval before cleaning up?


Hi, dev here.

Thanks so much for engaging :) I understand your point, here's sort of the philosophy behind the decisions we took regarding it:

The purpose of the app was to be as _hands off_ as possible. And because an LLM is involved in the mix, it might misclassify some emails and delete them.

For this reason, we label each email that we delete and it is possible to navigate to the email from the Run Status screen also, thereby allowing us to recover that email (if it was wrongly deleted). There is also a filter on the run status page to show all those emails marked for deletion.

In all our test runs, we found misclassification to be a minimum and hence we felt confident to go with this approach.

The "Schedule new cleanup" does indeed schedule a background task that does the actual inference + deletion.


Thanks a lot for following up!

It's great to learn you put quite some consideration into the workflow and the handling of deletions, gives me confidence into the tool.

I'd definitely share more of what you shared here in your read me or product demo video as well, I find it super relevant context for users.


That makes sense. I will make changes to the README and we will make a quick product video too :)


Really good article for someone who is interested in starting their deep learning career.


Thanks for the share @skun. Author here, open to questions and feedback.


In the next part of the blog series, we will showcase the performance across a multi-cluster of gpus.


Great job!


I am a co-founder of a company which has .xyz domain. We had a clear idea why we got .xyz domain but after 3-4 months of registration, we started seeing some issues with the domain. For starters, the visa office was unable to open our website to check the authenticity of our company before issuing visas for us to travel as their firewall had banned .xyz domain.

Some of our emails always was marked as spam when we were using it for marketing.

Thankfully, because of our organic growth .xyz did not hinder us too much but I personally think it will take a good time before .xyz is being used by commercial companies and hence I would suggest you to refrain from buying a .xyz domain for now.


Thank you, this is really helpful. I think we'll just go ahead and cough up the $1500 to acquire the .com version.


I'd recommend the same. We paid around the same for hackclub.com and it was definitely worth it (we started with hackclub.io).


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: