Cedric Ith
@cedricith
Followers
177
Following
523
Media
16
Statuses
156
founding designer @perceptroninc . previously @coinbase
Seattle
Joined May 2013
I’m excited to finally share the work we’ve been doing at Perceptron! Isaac v0.1 is our first model and is already wicked impressive at understanding images. Check it out → https://t.co/9RC5x3Rpnv
2
2
9
playing with flip dots as a filter after seeing the flip dot board at climate pledge arena
0
0
1
our 2 new model releases introduce Thinking among other capabilities like Tool use and structured outputs. take a peek 👇
Today we’re open-sourcing a preview of our two new models in the Isaac family: hybrid-reasoning 2B and 1B-parameter best-in-class vision-language models. Weights → https://t.co/1WgHMDfCST Blog → https://t.co/8MOLPKpUhO Demo → https://t.co/sAKt5dnZ6U
0
0
1
We’re excited to partner with Replicate in order to make our models more accessible to enterprises and developers. If you haven’t used Isaac 0.1, give it a try on Replicate!
🚨 Isaac 0.1 from @perceptroninc is now live on Replicate. It's a lightweight, grounded vision-language model that excels at OCR, spatial reasoning, and visual question answering. Read more here: https://t.co/48JOrf8hhj
1
3
11
Isaac-0.1 by @perceptroninc combines vision and language to bring multimodal intelligence to developers everywhere—now available as an API. The Perceptron platform, powered by Modal, delivers fast, reliable multimodal inference that scales automatically. Try it out 👇
Perceptron’s platform is here — built for Physical AI Developers can now use Isaac-0.1 or Qwen3VL 235B via: Perceptron API — fast, reliable multimodal intelligence Python SDK — simple, grounded prompting for vision + language Build apps that see and understand the world.
3
9
42
We’ve been integrating Isaac across the industry and have realized developers are missing a single platform for Physical AI – prompt engineering, deployment, and integration. Today we are excited to release Perceptron’s Platform - supporting our API - supporting chat
Perceptron’s platform is here — built for Physical AI Developers can now use Isaac-0.1 or Qwen3VL 235B via: Perceptron API — fast, reliable multimodal intelligence Python SDK — simple, grounded prompting for vision + language Build apps that see and understand the world.
2
3
15
Today, we unleash the beast 😤 (sound on 🔊)
Perceptron’s platform is here — built for Physical AI Developers can now use Isaac-0.1 or Qwen3VL 235B via: Perceptron API — fast, reliable multimodal intelligence Python SDK — simple, grounded prompting for vision + language Build apps that see and understand the world.
2
2
13
Perceptron’s platform is here — built for Physical AI Developers can now use Isaac-0.1 or Qwen3VL 235B via: Perceptron API — fast, reliable multimodal intelligence Python SDK — simple, grounded prompting for vision + language Build apps that see and understand the world.
6
17
96
I keep going back and forth between feeling blessed and feeling imposter syndrome by the fact that every time I open dwitter I can find at least one piece of work that moves me
0
0
5
Isaac 0.1 caught a few spots Neo missed — out of the box. At ~2B params, they could even run it on-board 👀
2
4
14
Excited to introduce Isaac - our first open-weights model which excels at localization and visual understanding.
1/ Introducing Isaac 0.1 — our first perceptive-language model. 2B params, open weights. Matches or beats models significantly larger on core perception. We are pushing the efficient frontier for physical AI. https://t.co/dJ1Wjh2ARK
5
11
70
Super excited to share what we've been up to at @perceptroninc Today we've released Isaac 0.1 — our first perceptive-language model: 2B params, but highly capable. Check it out: https://t.co/ohlQOUwxm3
1
4
11
Isaac combines object detection, spatial reasoning, and world knowledge to output responses like which climbing hold to reach for next. Excited to use this model as my personal climbing coach ;)
0
2
3
Learn more about Isaac v0.1 https://t.co/zm2Tlh4Iyz
1/ Introducing Isaac 0.1 — our first perceptive-language model. 2B params, open weights. Matches or beats models significantly larger on core perception. We are pushing the efficient frontier for physical AI. https://t.co/dJ1Wjh2ARK
1
0
3