
Hassan
@nutlope
Followers
94K
Following
30K
Media
628
Statuses
13K
Director of Developer Experience @togethercompute. Building open source AI apps (https://t.co/f8hbvXOFaN, https://t.co/SmHisRTtnp, https://t.co/H3xCBJvVMu, https://t.co/sed83e9OUA).
New York
Joined May 2015
Announcing Together Chat!. Use DeepSeek R1 & other top open source models to do web search, coding, image generation, & image analysis. Available today for free!
108
219
2K
You can try it out here for free (or use it through the @togethercompute API)!.
chat.together.ai
The premium AI chat experience.
0
0
4
Started hacking on an infinite word app!. Every word generated is a hyperlink you can click on to generate another page, which takes ~2s & costs $0.001!. Inspired by @dev_valladares's infinite wiki.
6
6
121
Tech stack & code:. ◆ @togethercompute inference API for transcriptions (Whisper) & transforms (Llama).◆ @vercel AI SDK for the LLM framework.◆ @neondatabase for the postgres DB .◆ @nextjs for the frontend/backend.◆ @ClerkDev for authentication.
github.com
Take notes with your voice & transform them with AI - Nutlope/whisper
4
5
73
We now have the fastest speeds for DeepSeek R1 – up to 330 tokens/sec running on B200s!. Here it is in action – video is not sped up!
Together AI Sets a New Bar: Fastest Inference for DeepSeek-R1-0528. We’ve upgraded the Together Inference Engine to run on @NVIDIA Blackwell GPUs—and the results speak for themselves:.📈 Highest known serverless throughput: 334 tokens/sec.🏃Fastest time to first answer token:
8
9
77