PulseAugur
中
实时 20:53:13
English(EN) I expected Jev to remember 2025. It doesn't know Trump was inaugurated

Jev语言模型不具备对过往事件的记忆

对Jev语言模型的最新分析显示,它不具备对过往事件的记忆,这与最初的预期相反。尽管Jev接受了海量文本的训练,但在其发布前最多20个月内已解决的预测市场结果上,它却无法回忆,在这些历史数据点上的表现仅略好于抛硬币。虽然Jev在与唐纳德·特朗普就职相关的市场上的得分略高,但其在包括美联储行动在内的其他历史市场上的表现一直很低,这表明它缺乏真正的记忆。 AI

影响 这一发现表明,当前的LLM可能无法有效保留对过往事件的知识,这影响了它们在历史预测或回忆任务中的可靠性。

排序理由 对LLM在历史数据上表现的分析。[lever_c_research降级:ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

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

Jev语言模型不具备对过往事件的记忆

本文如何被排名

Signal score
2 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
对LLM在历史数据上表现的分析。[lever_c_research降级:ic=1 ai=1.0]
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
model release, other
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Truong Pham | Moon The Train ·

    我曾以为Jev能记住2025年。它不知道特朗普已就任

    <p><strong>I expected Jev to have learned the outcomes of old prediction markets. It hasn't.</strong> Asked "Will Donald Trump be inaugurated?" about the January 2025 market, Jev says 0.70. Asked whether the Fed raised rates in January 2025, it says 0.30, the same number it gives…