Unverified50% confidenceFactExact time
The same large model placed in different harnesses can show vastly different capabilities: it may be just a chat box, or it may become an execution body that can read files, run commands, and call APIs.
1
Sources
50%
Confidence
Long-term
Relevance
10/21/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedBuilding a dedicated tool and prompt for the specific task of "proofreading" constrains the LLM to a supporting role more effectively than vague conversation through a general-purpose chat interface.71% similarUnverifiedA prompt-injected coding agent has access to the file system, terminal, Git credentials, and API keys, and usually has permission to execute commands directly, so its blast radius is far greater than that of an injected chatbot.71% similarVerifiedAgent mode is implemented through a 'tool-calling' mechanism, whereby the model can autonomously decide to call external APIs, execute shell commands, read and write files, or browse the web.71% similarUnverifiedPinduoduo once launched a chat feature where users could chat with a large number of 'people' in different roles; the barrier to this feature is low, and it can be implemented simply by connecting to a large model.71% similarUnverifiedThe message roles for the conversational generation interface include user (user query), assistant (AI), and system (system prompt), each with a different function.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1080134API
curl https://kongchang.com/api/v1/knowledge/claims/1080134MCP
get_claim(id=1080134)