Agents
Also please feel free to fight in the comments about 'pure LLMs' versus multimodal LLMs versus multimodal LLMs with tool use or whatever. I …
Ethan Mollick invited readers to discuss the distinctions between **pure large language models (LLMs)**, **multimodal LLMs** that process multiple data types (e.g., text, images), and **multimodal LLM
Ethan Mollick invited readers to discuss the distinctions between pure large language models (LLMs), multimodal LLMs that process multiple data types (e.g., text, images), and multimodal LLMs with tool use that integrate external APIs or software. He acknowledges key caveats for each approach but encourages debate in the comments to clarify what those differences truly imply.
Related
- I guess image input is the big capability of the models, and tool use can be a substitute for non-omni model output. Still, multimodal voice…
- TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
- EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
- Demo2: Multimodal Interactive Hybrid Agent
- MidTool: Mid-training Data Synthesis for Agentic Tool Use
Source: Ethan Mollick (X) | 2026-09-27