We're a research and product lab, unlocking the next step in AI reasoning capabilities. Visit us at elorian.ai
Palo Alto, CA
- Tweets 54
- Following 8
- Followers 6,363
- Likes 124
Pinned Tweet
Glimpse is our first model, built for visual thinking
Try it for yourself platform.elorian.ai/
Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that.
Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.
16
20
152
26,371
Sometimes the team goes out to do fun things
ChatGPT got me into AI via Ghibli style. Golf got me hooked on Glimpse 🏌️♂️
Going from text prompts to frame-by-frame video analysis is next level.
Try the demo: elorian.ai/blog/introducing-…
#Glimpse #ElorianAI
1
1
19
1,459
See how Glimpse works captions and labels robots
Glimpse is our first model, built for visual thinking
Try it for yourself platform.elorian.ai/
7
2
61
7,648
Today we're thrilled to announce the release of our first frontier visual reasoning model
56
121
1,772
119,529
Proud to partner with @fdesouza's team, @scale_AI, and @ScaleAILabs to introduce Humanity’s Sixth Sense (HSS) and set a new standard for how AI sees.
AI is usually measured on problems that are hard for people. Humanity’s Sixth Sense, our newest benchmark with @ElorianAI, tests the everyday visual judgements we make without thinking.
Humans scored 93.1%. The strongest AI model scored 53.6%.
labs.scale.com/blog/introduc…
2
8
56
152,702
Leading AI models can pass the bar exam but can’t tell if an apple will fit in a lunchbox
Meet Humanity’s Sixth Sense, our new benchmark with @ScaleAILabs. 522 questions testing the intuitive visual reasoning most humans find easy.
Blog: elorian.ai/blog/humanitys-si…
Benchmark: huggingface.co/datasets/Scal…
7
12
60
4,525
Our new brand identity and website celebrates how many true readings a figure can hold. Flat forms, solid color, the opportunity to mean something different to everyone who sees it - unconstrained by low resolution or grids. Check it out: elorian.ai
2
1
23
3,181
We’re growing the team at Elorian! Our mission: teach machines to truly understand the visual world. Small, focused team, no friction between idea and execution. If solving visual thinking excites you, check out our open roles: elorian.ai
3
9
87
10,672
Elorian AI retweeted
Another @JeffDean anecdote: in the pre-TensorFlow async training days, we were investigating why parameter updates were slow. A typical engineer would only read the C++ code, Jeff dug all the way into assembly code and found the extraneous memory load/lock instruction.
He also gave a great piece of advice: don't spend more than 3 or so years in a single project. Keep changing projects so you can keep learning. Great to see him stick to that!
27
84
2,137
394,972
Elorian has been named one of Forbes’ 25 Next Billion-Dollar Startups for 2026. Check it out:
Today we published the 12th edition of the Next Billion Dollar Startups list, a fun one because it spotlights up-and-comers working on everything from bone marrow transplants to thwarting biological threats. forbes.com/sites/richardniev…
9
38
20,682
How do we move visual AGI forward?
Our CEO @AndrewDai recently chatted with @bill_kerrrrr about Elorian's approach to visual reasoning, his journey from leading data for Gemini to founding Elorian, and what's ahead for our research and API.
Read the full interview: opensourceceo.com/p/andrew-d…
2
11
2,005
Our CEO @AndrewDai recently walked Isabelle Johannessen of @TechCrunch through our early beginnings, and how he pitched building the future of visual thinking to investors.
Check out the latest episode of Build Mode here:
This founder left his job at Google and raised a $55M pre-seed with a $300M valuation in just five months, even including some non-technical VCs.
In this week's episode of Build Mode, co-founder Andrew Dai breaks down how they pulled off @ElorianAI's ascent before building a product or landing customers: spr.ly/6016BEZv6g
2
4
13
382,858
Our CEO @AndrewDai and @rocketalignment on @theinformation TV, discussing gaps in visual reasoning skills
nitter.siddz.com/theinformation/status/…
The Information
AI only has pre-schooler level capabilities for visual tasks.
"The frontier models—the best of them—still reason around the age of a preschooler, and any elementary school kid in that benchmark was able to beat all the frontier models on these visual tasks."
"These are tasks that are not just object recognition. It's about spatial reasoning... tasks like navigating through the maze…” — @AndrewDai, CEO of Elorian
2
5
1,583
Elorian AI retweeted
The world is made of objects, space, motion, and spatial relationships, not text. Imagine having to describe Karl the Fog to someone without pointing to a picture. That's why we believe visual reasoning is one of the next major frontiers in AI.
Appreciate Ethan, Zara, and the Unicorner team for telling our story. Check it out:
How’s it going? Check out this week's edition of The Highlight for more.
read.unicorner.news/p/eloria…
3
21
4,444
Toddlers see better than AI... here's why that's a problem theneurondaily.com/p/watch-e…
3
9
1,884
We’re thrilled to welcome @dustinvtran to Elorian as our Chief Reasoning Architect.
After leading post-training at xAI and contributing to Gemini at Google DeepMind, Dustin is joining Elorian to help build the next generation of visual reasoning models.
Excited for what's ahead 🚀
personal news: i've joined Elorian as Chief Reasoning Architect. multimodal AGI is the most critical frontier as we move from the era of chatbots to coding agents to models that reason and act over the physical world. i'm really excited to design natively visual models across thinking, agents, architectures, and the systems stack with the amazing team at Elorian.
i wish the best to everyone at xAI & SpaceX — driving posttraining was a unique experience with so many memorable stories. all the best to the team, and to Elon.
6
30
3,153
If you're at CVPR come by to discuss why so many labs have struggled to succeed at visual reasoning . We're pretty sure there will be snacks.
@ElorianAI is co-hosting a dinner event in CVPR to discuss the reasoning gap in visual AI, together with @gmi_cloud @NVIDIAAI, @NEA , and @twelvelabs .
RSVP and join us ! Link: luma.com/gmicloud-9gof
1
5
2,040