pauljeba

How do I beleive you? You wrote this post by hand. lol

How do I beleive thi? you wrote this blog by hand.lol

No not another AI Image generator.

No, it doesnt do everything.

No. Not perfect.

But does work, 1 in 5 generations still wonky.

But reasonably beneficial.

I'm Paul, founder of Two Minute Reports.

Running repetitive reports for your business is a tedious task. It's quite a waste of time and efforts. We experienced this ourselves as well. This is the reason why we founded Two Minute Reports.

Basically we are automating all the time consuming tasks regarding reporting and data insights, directly in Google Sheets.

Looking forward to hearing your feedback!

Thank you. Corrected as per your suggestion.

No, its for people who want to send regular reports. Cooking is there because, as a user, you dont need to be in front of the computer to send reports.

You could be doing anything like cooking or driving. Wanted to extend to work-life balance kind of examples and cooking seemed to be a good example.

Since the code of GTP-3 is behind closed doors, can we re-purpose GPT-2, to create a slightly less efficient clone?

What do you look for in a trailler ? Could you describe the process in few words?

Exactly, free time is a premium and has to be treasured.

I think a quiz like what you meantioned would be effective. The problem is finding data that could help power such a quiz. Example, a #tag of #sad could be assigned to a movie that's just 20% sad, leading to misuse/misinterpretation. What we may need is a variable-tag metric... But I don't think there is any available data for this yet..

You are very right, especially with the challenges in making it successful. Crowd sourcing or Machine Learning are the options I guess, each with its pros and cons.

I like these profile based recommendations, but they tend to be black box ones. They miss out on the how I may like a future movie that I have not come across before. I like how nomadlist.com has done it for places. You can easily figure out which place to go, just using their fitlers.

Would a similar filter be useful for movies?

What about multiple metrics, which each can talk about specific aspects of why someone would watch a movie. I could then weigh these metrics as per my preference and choose the movie of my liking. Do you get it?

Yes, that's how most recommendations are being effected. I think we need also an explicit way of communicating our preferences, and getting scores against them. The problem with recommendations is, they are not transparent enough and can fail.

Yes, emotions- "how does one feel while watching the movie". This is missing from the traditional genre tagging - "whats the movie about"

If you look at what nomadlist.com has done for places - I can easily figure out if I would like to visit a place or not, by selecting their emoji based filters.. I think a similar emoji based rating, that could say how sad a movie is, how happy a movies is, etc, could be useful. What you think?

You mean the genre tags, like crime, thriller, etc?

I like letterboxd, but unless I read through all the comments, I can't make out if I would like a movie or not. There scoring is similar to imdb. I dont think just a simple rating system would be a solution.

I am really looking for an answer to this. I promise to incorporate the best answer arriving out of our discussion in my site flixcatalog.com. I don't think the existing filter on imdb scores makes sense.

Yeah packaging this as a B2B solution is something that I have been thinking for a long time. Do let me know if you have any specific interest on this. Will be glad to work closer with you on this.

This is definitely something I will use in one of my apps. Thanks for building.

Ahh yeah :) That's my trade secret :D If there is more interest from the community I would definitely share that here. Until then I will keep it as a secret :) Hope you dont mind.

I use some amount of opencv magic and machine learning to remove the background. Have you checked the quality of the background removal process, were you satisfied?