Unverified60% confidenceFactExact time
Mainstream large language models such as GPT-4 and Claude are based on the Transformer architecture; each inference is an independent forward-pass computation with no built-in mechanism for maintaining state across requests.
2
Sources
60%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
VerifiedThe core working principle of large language models such as GPT-4, Claude, and Gemini is next-token prediction based on the Transformer architecture.83% similarUnverifiedCurrent mainstream AI large models such as GPT-4, DeepSeek, and Claude are essentially large-scale language models based on the Transformer architecture.81% similarUnverifiedA reusable set of prompt patterns can work stably across models, and whether using GPT-4, Claude, or Llama, the core logic is the same.78% similarVerifiedGPT-4 and Claude are large language models that can understand context, generate structured outputs, and execute multi-step reasoning76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/517996API
curl https://kongchang.com/api/v1/knowledge/claims/517996MCP
get_claim(id=517996)