Agents
You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination…
You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomo
You can't solve real-world physical tasks through autoregressive sampling alone. The physical world is entirely unforgiving to hallucination or approximate pattern matching. If we want actual autonomous robotics we have to engineer causality and discrete reasoning back into the loop. Biwei and the team at Aether AI is doing exactly the kind of foundational, non-consensus work the field actually needs right now. I have spent more than a decade studying causality. For me, causality is about understanding the rules that govern how actions change the world, and reasoning about their consequences before acting. Scaling has made today's models remarkably capable at spotting patterns and predi…
Related
- ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering
- Most human tasks are not Markovian, the optimal next action cannot be determined solely by looking at the current state. It depends heavily …
- Don't Solve, Just Compare: Tiny Advisors for Runtime Intervention in LLM Agents
- Uncertainty Quantification for LLM Function-Calling
- When an agent is allowed to decompose a goal into smaller sub-tasks, it frequently suffers from goal drift. Left unchecked, it will redefine…
Source: Francois Chollet (X) | 2026-10-14