Expired50% confidenceOpinionExact time
Ryan Lopopolo believes that the methodologies he shares are essentially all prompt engineering and require no changes to model weights whatsoever.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 9/30/2026(expired)
Sources
OpenAI Engineer's Practice: Agent-Driven Development Methodology in the Era of Free Code
bilibili赛博门外憨6/10/2026
Related Claims
UnverifiedLLM采用无状态设计，模型权重在训练后被固化，推理时不会因某次对话而改变内部参数62% similarUnverifiedThe prompts submitted to the models did not include question-type hints, requiring the models to determine the question type on their own.60% similarVerifiedLoRA是以参数高效微调（PEFT）为代表的主流微调方法，核心思想是在不改动原始模型权重的前提下向特定层注入低秩矩阵，只训练新增参数60% similarVerifiedWith LoRA, the weights can be merged back into the original model at inference time, introducing no additional latency59% similarUnverified提示词工程本质上是利用模型已有能力提供更多相关信息，并未扩展模型的能力边界58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/49505API
curl https://kongchang.com/api/v1/knowledge/claims/49505MCP
get_claim(id=49505)