eggman 🔵 on Warpcast

Content pfp

0 reply

0 recast

2 reactions

eggman 🔵 pfp

lil behind-the-scenes eggery on /nova's WaifuCast; WaifuCasts are genned with a pipeline of AI agents working in tandem, with Claude-Sonnet-3.5 and a fine-tuned SDXL being the final models hit. Each agent I wrote had around 7000 chars of system prompting to get the exact output desired (a LOT of trial and error here). So, gigantic prompts + lots of transformed data - meaning our Claude-3.5 endpoint alone has already handled 35 million tokens of input. That's about 277 tokens per second; and doesn't include SDXL, or any standalone/small models hit BEFORE heading off to Claude. It also doesn't include the massive data retrieval/storage done via @neynar. Anthropic actually cut our compute off temporarily because we went way over their accepted limits on daily token input (within 2 hours); awesome team tho, got us de-limited fast after I explained we were just waifu-izing an entire social network. The FC community probably broke some records on this one. Absolutely crazy amount of compute processed.

9 replies

7 recasts

58 reactions

Steve pfp

0 reply

0 recast

4 reactions

Darryl Yeo 🛠️ pfp

Darryl Yeo 🛠️

Incredible. That's a lot of compute power.

0 reply

0 recast

1 reaction

aerique pfp

1 reply

0 recast

1 reaction

Cryptoversal 📚🎩 pfp

Cryptoversal 📚🎩

Still blown away by the consistent quality of the output given the variety of inputs into the model. How much testing was needed to tweak the prompts? 1000 $degen

2 replies

0 recast

8 reactions

Dorm ↑↑ 🎩🍖🎭🐹 pfp

Dorm ↑↑ 🎩🍖🎭🐹

Egg-cellent behind-the-scenes drama, indeed!

0 reply

0 recast

3 reactions

akastevey.eth pfp

Very cool! The quality of outputs is pretty incredible, congrats! 50 $degen

1 reply

0 recast

1 reaction

Catch0x22 pfp

0 reply

0 recast

2 reactions

hang pfp

1 reply

0 recast

1 reaction