Unverified50% confidenceFactExact time
A jailbroken model refers to a large language model whose built-in safety filtering mechanisms have been bypassed through prompt engineering techniques or technical methods to produce restricted content.
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAn uncensored model is a model version in which the safety alignment restrictions injected during the training phase of a large language model are removed or weakened through fine-tuning.79% similarUnverifiedThe 'uncensored' nature of language models involves alignment strategies at the level of model behavior, whereas the 'uncensored' nature of image generation models is merely a switch for a post-processing filtering step in the inference pipeline.78% similarUnverifiedWhen constraining output format through prompts, the model may forget these constraints in long conversations or complex reasoning scenarios.77% similarUnverifiedAn uncensored model refers to a model variant in which refusal behaviors implanted during the RLHF and safety fine-tuning stages are removed through post-processing means.75% similarUnverifiedCommon system prompt extraction techniques include directly asking the model to output its system prompt, using role-playing to bypass restrictions, and exploiting the model's tendency toward excessive compliance for indirect elicitation.75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948951API
curl https://kongchang.com/api/v1/knowledge/claims/948951MCP
get_claim(id=948951)