DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: A reasoning hierarchical robotics pipeline you can run in the browser
This demo combines the flexible task programming and reasoning of Gemini ER (what is the scene, and what should I do?) and classical camera calibration, kinematics, motion controllers. Each layer is independently swappable, and the AI model doesn't need to know anything about the robot's embodiment. This recreates the modularity of a Sense-Plan-Act architecture while retaining the semantic reasoning of a foundation AI model. A writeup explaining the tradeoffs is linked from the page <a href="https://www.avikde.me/building-a-reasoning-hierarchical" rel="nofollow">https://www.avikde.me/building-a-reasoning-hierarchical</a>.
This project tackles the 'holy grail' of robotics—embodiment-agnostic reasoning—by cleverly decoupling high-level LLM logic from low-level classical control. While currently a technical demo with minimal traction, the modular architecture addresses significant industry pain points regarding interoperability and the 'black box' nature of end-to-end neural controllers.