Agents
It is ironic that the thing that is now most annoying about long-running agentic tasks with Large Language Models isn't coding or errors or …
It is ironic that the thing that is now most annoying about long-running agentic tasks with Large Language Models isn't coding or errors or hallucinations, but the fact that their language gets worse
It is ironic that the thing that is now most annoying about long-running agentic tasks with Large Language Models isn't coding or errors or hallucinations, but the fact that their language gets worse due to drift as a task goes on Its in your the name! Just write better already!
Related
- AdaLens: Interactive Storyline for Monitoring and Steering Long-Running Agentic Data Analysis
- MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memory
- ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
- When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
Source: Ethan Mollick (X) | 2026-09-20