hagope

The long press blurred image thing was a disaster, the app no longer usable.

this is great, I've always wanted something like this, do you think you can add other model metadata, like api name (`gemini-2.5-pro`), context length, modalities, etc

Anthropic and all the AI vendors need to implement "Login with ___" allowing users to trust sites to use their own AI resources, similar to how Dropbox allows 3rd party access to the User's storage. Most users don't want to bother with generating and loading API keys, nor can they manage it safely.

I used to be excited about running models locally (LLM, stable diffusion etc) on my Mac, PC, etc. But now I have resigned to the fact that most useful AI compute will mostly be in the cloud. Sure, I can run some slow Llama3 models on my home network, but why bother when it is so cheap or free to run it on a cloud service? I know Apple is pushing local AI models; however, I have serious reservations about the impact on battery performance.

I can confirm it is TOTAL tokens, this from the account/usage page:

gpt-3.5-turbo-0301, 2 requests 28 prompt + 64 completion = 92 tokens

This is really cool! Are you using OpenAI API under the hood or have you trained your own model?

If the entity doesn't exist, wouldn't it violate the FK and therefore no need for the nullable constraint?

in that scenario why not use foreign key? any advantage to using constraint?

This is cool, but wouldn't creating a constraint using a nullable column be considered a poor design decision? In which scenarios would this be a good idea?

Would be cool if you could enter Yotube URL and you parse out the recipe from the audio/video.

Also, what if people move every year? are they going to readjust after every move?

They should have also renamed the parent company to Face, Inc.