AI & Tech • Digital Trends Exploring ideas shaping the future ✨
New York, USA
Joined June 2011
- Tweets3.6K
- Following274
- Followers13.2K
- Likes206
Mayra James retweeted
The stat I'd want next to the 19 seconds: how many tasks a day people start. That's where half a minute each turns into an afternoon.
🤝 Paid partnership
Today we’re introducing Aether @aetherruntime.
The fastest cloud coding agents in the world that you can use with your existing subscription
Give it a task and just 20 seconds later your build is running on its own cloud machine. You can pick up from your phone, watch every line, and step in whenever you want as if it was local. Close the laptop. It keeps going.
It runs Claude Code or Codex on the Claude or ChatGPT plan you already pay for so there’s not a 2nd AI bill. You only pay for the machine.
When it’s done, if code review is enabled, a reviewer agent runs the code with the changes, which catches classes of bugs that can't be found from static analysis.
Before building Aether I built infra at Apple, Uber, and HeyGen. I built Aether because the cloud agents I tried before all had drawbacks, and I couldn't imagine building something without it now.
It’s free to start. runaether.dev
Mayra James retweeted
If your team runs on handoffs, SenseNova 6.8 Flash's TeamBench score (53.33, top of its chart) and cross-session memory are the two things to look at first. Handoffs are where context usually gets lost.
Get your team on it: platform.sensenova.ai/docs
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
One thing that stands out about Ornith 1.5 is its focus on both capability and efficiency. That balance matters when deploying large AI models.
🤝 Paid partnership
Aloha!🌺 Meet Ornith-1.5-122B: No Tradeoff Between Strong and Fast
Stronger. Faster. Leaner. Ornith-1.5-122B delivers frontier-level capabilities with exceptional inference efficiency. With superior instruction following, stronger task decomposition, and deeper understanding of real-world workflows, it achieves state-of-the-art performance among open-source models of comparable size, while running on a single NVIDIA DGX card!!
Open weights under the MIT license.
Coding
✅SWE-bench Verified: 0.845
✅TB2.1: 0.813
✅CyberGym: 0.800
✅NL2Repo: 0.512
Agentic
✅HLE: 0.446
✅BrowseComp: 0.785
✅MCP-Atlas: 0.746
✅Toolathlon: 0.708
🤗Hugging Face: huggingface.co/ornith-ai/Orn…
We can’t wait to see what you build with Ornith-1.5-122B.
Mayra James retweeted
High-quality video is becoming less expensive, more accessible, and much faster to produce.
🤝 Paid partnership
We're releasing HeyGen Video, built for businesses that need production-quality video without production-level costs.
Pricing starts at $0.01/s through October (50% off)
Built on @Minimax_AI H3, post-trained by HeyGen.
Learn more: developers.heygen.com/heygen…
Mayra James retweeted
The open source crowd gets something this cycle too: SenseNova Loop-9B-Preview, a 9B Looped Transformer preview. SenseNova 6.8 Flash is the headline, Loop is the one researchers will want to dig into.
SenseNova-Loop:
github.com/OpenSenseNova/Sen…
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
ok SenseNova 6.8 Flash making editable blender projects and three.js scenes from a prompt is kind of wild. the aurora camp demo even has a spiral staircase with handrails around a central axis lol
you can try it here 👇
platform.sensenova.ai/docs
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
Every agent PR ends with ""all tests pass"". Aether's reviewer opens the app, clicks through the change and leaves a recording on the PR. That's the test I actually wanted.
🤝 Paid partnership
Today we’re introducing Aether @aetherruntime.
The fastest cloud coding agents in the world that you can use with your existing subscription
Give it a task and just 20 seconds later your build is running on its own cloud machine. You can pick up from your phone, watch every line, and step in whenever you want as if it was local. Close the laptop. It keeps going.
It runs Claude Code or Codex on the Claude or ChatGPT plan you already pay for so there’s not a 2nd AI bill. You only pay for the machine.
When it’s done, if code review is enabled, a reviewer agent runs the code with the changes, which catches classes of bugs that can't be found from static analysis.
Before building Aether I built infra at Apple, Uber, and HeyGen. I built Aether because the cloud agents I tried before all had drawbacks, and I couldn't imagine building something without it now.
It’s free to start. runaether.dev
Mayra James retweeted
Just came across OXR and had to share 🙌
Beats everyone on olmOCR-Bench + OmniDocBench + DocParsingBench, and no open-source parser was quicker on its RTX PRO 6000 test.
100 pages in 101 s. LightOnOCR-2-1B: 171.7 s.
Tables, formulas, chemical structures. Replace the layout model. 1.3B, RSI, reads and orders in one parallel pass.
github.com/SoMarkAI/OXR
🤝 Paid partnership
Mayra James retweeted
the part to read here is the review step. it runs the app in a browser and leaves screenshots plus a recording on the PR before anyone looks.
🤝 Paid partnership
Today we’re introducing Aether @aetherruntime.
The fastest cloud coding agents in the world that you can use with your existing subscription
Give it a task and just 20 seconds later your build is running on its own cloud machine. You can pick up from your phone, watch every line, and step in whenever you want as if it was local. Close the laptop. It keeps going.
It runs Claude Code or Codex on the Claude or ChatGPT plan you already pay for so there’s not a 2nd AI bill. You only pay for the machine.
When it’s done, if code review is enabled, a reviewer agent runs the code with the changes, which catches classes of bugs that can't be found from static analysis.
Before building Aether I built infra at Apple, Uber, and HeyGen. I built Aether because the cloud agents I tried before all had drawbacks, and I couldn't imagine building something without it now.
It’s free to start. runaether.dev
Mayra James retweeted
Frontend devs: SenseNova 6.8 Flash outputs web pages and Three.js scenes you can open and change. That's the difference between a pretty demo and an actual starting point for a project.
Start with the Token Plan:
platform.sensenova.ai/docs
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
Question for ML folks: how far can looping a 9B model go vs stacking more layers? SenseNova Loop-9B-Preview is SenseTime's open source testbed for that. Separate research from SenseNova 6.8 Flash.
SenseNova-Loop:
github.com/OpenSenseNova/Sen…
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
What the scan reads correctly is probably the harder part to get right.
🤝 Paid partnership
Mayra James retweeted
claude code people, someone run an overnight refactor on this and tell me how it does
🤝 Paid partnership
Today we’re introducing Aether @aetherruntime.
The fastest cloud coding agents in the world that you can use with your existing subscription
Give it a task and just 20 seconds later your build is running on its own cloud machine. You can pick up from your phone, watch every line, and step in whenever you want as if it was local. Close the laptop. It keeps going.
It runs Claude Code or Codex on the Claude or ChatGPT plan you already pay for so there’s not a 2nd AI bill. You only pay for the machine.
When it’s done, if code review is enabled, a reviewer agent runs the code with the changes, which catches classes of bugs that can't be found from static analysis.
Before building Aether I built infra at Apple, Uber, and HeyGen. I built Aether because the cloud agents I tried before all had drawbacks, and I couldn't imagine building something without it now.
It’s free to start. runaether.dev
Mayra James retweeted
Publish this to cool math games!
I asked Claude to build an office for the @tavus PALs...
I was not expecting it to build THAT kind of office
Mayra James retweeted
Ok ok ok ok ok ok ok ok fine i will play.
I asked Claude to build an office for the @tavus PALs...
I was not expecting it to build THAT kind of office
Mayra James retweeted
On both Hugging Face and GitHub: SenseNova Loop-9B-Preview, SenseTime's 9B Looped Transformer research model. Not to be confused with SenseNova 6.8 Flash, the agent model. Different jobs entirely.
SenseNova-Loop:
github.com/OpenSenseNova/Sen…
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
Cloud development just got a whole lot faster. Aether is changing the game.
🤝 Paid partnership
Today we’re introducing Aether @aetherruntime.
The fastest cloud coding agents in the world that you can use with your existing subscription
Give it a task and just 20 seconds later your build is running on its own cloud machine. You can pick up from your phone, watch every line, and step in whenever you want as if it was local. Close the laptop. It keeps going.
It runs Claude Code or Codex on the Claude or ChatGPT plan you already pay for so there’s not a 2nd AI bill. You only pay for the machine.
When it’s done, if code review is enabled, a reviewer agent runs the code with the changes, which catches classes of bugs that can't be found from static analysis.
Before building Aether I built infra at Apple, Uber, and HeyGen. I built Aether because the cloud agents I tried before all had drawbacks, and I couldn't imagine building something without it now.
It’s free to start. runaether.dev
Mayra James retweeted
Every agent demo looks good in session one. The real test is session ten. SenseNova 6.8 Flash is built for that with long-term memory and cross-session collaboration, and LongMemEval-S 93.33 backs it.
Start your session one:
platform.sensenova.ai/docs
🤝 Paid partnership
𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝟲.𝟴 𝗙𝗹𝗮𝘀𝗵 𝗶𝘀 𝗵𝗲𝗿𝗲!
𝗥𝗲𝗹𝗶𝗮𝗯𝗹𝗲 𝗪𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀. 𝗕𝗲𝗮𝘂𝘁𝗶𝗳𝘂𝗹 𝗗𝗲𝘀𝗶𝗴𝗻.
🧠 𝗢𝗳𝗳𝗶𝗰𝗲 𝗜𝗻𝘁𝗲𝗹𝗹𝗶𝗴𝗲𝗻𝗰𝗲: 𝗟𝗼𝗻𝗴-𝘁𝗲𝗿𝗺 𝗺𝗲𝗺𝗼𝗿𝘆 & 𝗽𝗿𝗼𝗮𝗰𝘁𝗶𝘃𝗲 𝗶𝗻𝘁𝗲𝗿𝗮𝗰𝘁𝗶𝗼𝗻 𝘁hat remember your needs and keep tasks moving.
🎨 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗗𝗲𝘀𝗶𝗴𝗻: Animated PPTs, motion posters, interactive websites & editable Blender 3D projects.
Beyond content generation — getting things done and delivering polished, ready-to-use results.
𝗧𝗿𝘆 𝗶𝘁 𝗳𝗼𝗿 𝗙𝗥𝗘𝗘 𝗼𝗻 𝗦𝗲𝗻𝘀𝗲𝗡𝗼𝘃𝗮 𝗧𝗼𝗸𝗲𝗻 𝗣𝗹𝗮𝗻!
𝗚𝗲𝘁 𝟭,𝟱𝟬𝟬 𝗙𝗥𝗘𝗘 𝗔𝗣𝗜 𝗿𝗲𝗾𝘂𝗲𝘀𝘁𝘀 𝗲𝘃𝗲𝗿𝘆 𝟱 𝗵𝗼𝘂𝗿𝘀.
🔑 Get your API key: platform.sensenova.ai
🤖 Model ID: SenseNova 6.8 Flash
👾Discord: discord.com/invite/BuTXPHmQu…
Mayra James retweeted
Tight feedback loop, model edition. On annotation-free docs, a general-purpose VLM calls out errors and low-confidence results; disagreeing rollouts surface as uncertain; clustering links shared causes; the VLM writes the round N+1's data. No manual labels. First RSI loop in doc parsing. Light, swappable layout model; one model reads and orders in parallel. Highest on olmOCR-Bench / OmniDocBench / DocParsingBench; 6.77x Surya-OCR-2 on an RTX PRO 6000.
github.com/SoMarkAI/OXR
🤝 Paid partnership
Mayra James retweeted
Multiplayer support?
I asked Claude to build an office for the @tavus PALs...
I was not expecting it to build THAT kind of office