Unverified50% confidenceCautionExact time
When using hosted models, all transcript conversation records during the testing process leave the local machine and are sent to third-party hosts; it is recommended to check data policies or use Ollama to run models locally.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedUsing the command ollama run <model name> will automatically detect whether the model is already available locally; if not, it will download it and then enter conversation mode upon completion.74% similarUnverifiedAfter the interview ends, the system automatically transcribes the recording and inputs the complete conversation record into the large model, generating a structured evaluation report across dimensions such as expressive logic, professional skills match, and communication ability via a Prompt template.66% similarUnverifiedExternal text reaching the model (emails, web pages, webhooks) may carry injected instructions targeting the model, so model output should never directly trigger deletions, sends, or payments—a whitelist or code check should be placed in between.65% similarUnverifiedWhen a single-turn model receives input containing assistant replies or tool call history, LLM will raise an `llm.ConversationNotSupported` exception, and the `llm chat` command will also reject such models before the session begins.65% similarUnverifiedIn multi-turn conversations, the System message sets the behavioral tone and constraints, the user message represents user input, and the assistant message is the model's historical replies.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/995711API
curl https://kongchang.com/api/v1/knowledge/claims/995711MCP
get_claim(id=995711)