Leveled up in the Great Gas Reckoning with ETHGas! 💪
Teen Jack status: 0.7721 ETH gas spent, 350 Beans earned—supporting the Gasless Future!
Claim your Gas ID at https://t.co/rjJAEaGivv
2/ Products of the GRID
Recursive Open Meta Agent (ROMA): Multi-agent framework that breaks down complex queries into smaller, more achievable tasks. The first use-case (deep research) outperforms all existing deep research model platforms and is open for builders to fork/improve.
Open Deep Search (ODS): Open-source search framework that splits reasoning, search, and calculation tasks, achieving SOTA performance on standard search benchmarks.
Dobby: Open-source model that was one of the first models to prioritize human-like values (tone, loyalty/core beliefs, etc.) and built through 2M+ community members’ feedback.
Fingerprinting: Training library/method that protects a model’s identity, ensuring that open-source developers can verifiably prove their model ownership even if the model weights are fully revealed.
Sentient Chat: AI platform that coordinates intelligence within the GRID, providing a UI interface to the world's largest network of intelligence.
Our newest piece of the GRID just got an upgrade 😁
GRID is the world’s largest network of intelligence, containing agents, models, data sources, frameworks, and Sentient Chat—the infrastructure that stitches it all together.
Our newest piece of the GRID just got an upgrade 😁
GRID is the world’s largest network of intelligence, containing agents, models, data sources, frameworks, and Sentient Chat—the infrastructure that stitches it all together.
🎉 1 MILLION QUESTIONS ANSWERED ON SENTIENT CHAT
Thank you to everyone for using Sentient Chat and working to improve this platform every day. Platform usage has skyrocketed as we introduce more agents, models, and ecosystem partners.
Back to building, we’re coming for the big boys😈
The Week of Dobby:
6/2: The Dobby Report
6/4: ???
6/6: ??????? (more question marks because it's even bigger😁)
For tomorrow, likes + retweets = spots available (iykyk)
Reinventing LLM Training: The First LLM to Seamlessly Combine Tone, Value Alignment, and Rigorous Reasoning
At Sentient, we are enabling an open AI ecosystem to deliver the best user experience possible. As part of that goal, we have been conducting research into building the most effective post-training pipeline for LLMs to be optimized on certain dimensions (practical performance, tone, value, and safety alignment) for their specific use-case.
Current AI excels at hard skills (math, coding, broad knowledge) but fails to emulate human communication (humor, tone, empathy, etc.). Our recent work on the extended Dobby family shows it’s possible to fuse top-tier hard skill performance with genuine soft skills.
Read the full paper here (we think you’ll enjoy the way it’s written, no technical knowledge needed😁):
👉 https://t.co/Fit1MGQgAW
Check out our blog highlighting the main breakthroughs:
👉 https://t.co/6PuHB7BXeb
Announcing ROMA (Recursive Open Meta Agent): our new multi-agent framework that sets SOTA in reasoning + search.
Seal-0: 45.6%
FRAMES: 81.7%
SimpleQA: 93.9%
🧵 Read more about how recursive coordination lets agents tackle complex queries.
As GRID continues to grow as the world’s largest network of intelligence, we’re excited to onboard and showcase partners across the AI stack.
🧵Here’s a look at some of the partners fueling the model and verifiable AI experience
The GRID is designed to turn frontier research into shared, open infrastructure.
Open Deep Search (ODS) is one of our proudest additions: a modular retrieval + reasoning framework that shows how open-source systems can outperform proprietary stacks on real benchmarks. Fully forkable and extensible, ODS is available for anyone to integrate, adapt, and build on inside and outside the GRID.
🧵 Check out how we created the best open-source search framework that outperforms ChatGPT and Perplexity, all contributing to GRID.