zdwolfe

I find it odd that any LLM could be considered open source. Sure the weights are available to download and use, but you can't reasonably reconstruct the output model as it's impractical for an individual to gather a useful dataset or spend $5,000,000+ of GPU time training.

Yes, and so far I haven't been able to combat it.

I'm working on a dumb tool to picture-in-picture show rendered GPS data as a mini-map with a forward- and backward-looking trail on top of GoPro footage (to memorialize cool bike rides).

Thanks for these stats, it changes how I think about aluminum packaging/cans.

I much prefer Fabric server to Paper. Paper has a couple game-breaking differences in advanced redstone, and Fabric in general has more mod compatibility. There are options to disable the redstone differences, but it's a bit annoying.

I use this extensively, it's so wonderful

This is perfect. I've tried many noise apps in the past and I'll be using this for a long time I'm sure.

Feature request: Deep-links so I can share or bookmark a 'preset'.

This is really cool but I will never trust an app like this to have access to my emails.

Seems to not be working. I tried the same prompt twice. My trial credits were used but there was no image generated, nor do they appear in My Images.

Wow, that was cool. Felt like the intro to a game I'd want to play.

Looks cool, thanks for making this.

Not OP, but I too wrote something nearly identical with whisper so I could creep on old EthosLab videos. Here's the gist:

from pytube import Channel

import whisper

channel_yt = Channel(channel_url)

video_yt = channel_yt.videos[0]

video_yt_stream = video_yt.streams.filter(mime_type="video/mp4").filter(res="720p").first()

video_yt_video_file_path = video_yt_stream.download()

audio = whisper.load_audio(video_yt_video_file_path)

model = whisper.load_model("tiny")

transcript = model.transcribe(audio)

Neat, I am working on something similar with almost all the same tech you mentioned (CDK, R53, TS, APIGW+Lambda), and a Dockerized dev env with everything set up. It's meant to be a boilerplate I copy for new side projects. DM me on twitter (same username) if you'd like to compare notes or collaborate.