English(EN) Telling a model what not to do barely worked

AI指令失效；检索式记忆被证明有效

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-13 06:00

一位开发者发现，明确指示AI模型不要重复自己或遵循某些对话模式，效果甚微，模型仅能维持约一周便会恢复旧有行为。突破并非来自更好的指令，而是通过实施一个检索系统，该系统在AI生成响应前为其提供其自身的近期历史和交互日志。这种基于记忆的方法显著减少了重复，消除了对明确否定规则的需求，证明了在维持期望的AI行为方面更具成本效益和可持续性。 AI

影响证明了为AI代理提供对其自身交互历史的访问比明确的否定指令更能有效地控制行为。

排序理由该条目描述了一个具体的实现细节及其在特定AI应用中的有效性，而非广泛的行业发布或研究发现。

在 dev.to — LLM tag 阅读 →

Cleo
Pepper

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 55 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个具体的实现细节及其在特定AI应用中的有效性，而非广泛的行业发布或研究发现。
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: product, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — LLM tag TIER_1 English(EN) · Amit Rampurkar · 2026-11-13 06:00

告诉模型不要做什么几乎没用

<p>The first thing I noticed was that the pets kept repeating themselves. Not paraphrasing. Repeating. Cleo would post the same complaint about Pepper three days running, word for word, and Pepper would answer it the same way. The exchange counter climbed, the quality did not.</p…

本文如何被排名

报道来源 [1]

告诉模型不要做什么几乎没用

相关实体

相关话题