Unverified50% confidenceFactExact time
The language model receives a single flat stream of text containing the system prompt, user messages, retrieved documents and tool return results, with no reliable way to distinguish instructions from ordinary content.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedA language model never calls tools directly; it only outputs a piece of text stating which tool it wants to call, after which code executes the call and returns the result as text.76% similarUnverifiedWith the introduction of large language models, a lead scoring system can understand free-text fields in forms and judge purchase intent, budget signals, and urgency at the semantic level, rather than relying solely on structured fields.75% similarUnverifiedA language model itself can only generate text and cannot directly access a database or know a user's order status; it must use a tool-calling mechanism to perform actual operations.74% similarVerifiedThe root cause of Prompt Injection is that large models cannot structurally distinguish between "system instructions" and "user data," as both are presented as natural language text at input time.74% similarUnverifiedA model is essentially just a function: text in, text out, with no ability to search the web, read files, run code, or remember the previous message.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047763API
curl https://kongchang.com/api/v1/knowledge/claims/1047763MCP
get_claim(id=1047763)