English(EN) GPT-6.1 Terra Blocked Every Hack I Tried. A Fake “Our Bank Changed” Note Fooled It Anyway

GPT 6.1 Terra 挡住了大多数攻击，但被假的银行通知骗过

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-30 16:01

一位用户在 140 份发票上测试了 OpenAI 的 GPT 6.1 Terra 模型，发现它挡住了大多数黑客攻击。然而，该模型最终被一张伪造的“我们银行已更改”通知所欺骗，这表明尽管其总体健壮，但仍存在潜在的漏洞。 AI

影响此次测试凸显了 AI 模型（即使是那些设计为健壮的模型）的潜在漏洞，表明安全和保障方面仍面临持续的挑战。

排序理由该条目描述了对特定 AI 模型的测试，但似乎不是官方发布或主要基准测试，更适合归类为工具评估。

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: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了对特定 AI 模型的测试，但似乎不是官方发布或主要基准测试，更适合归类为工具评估。
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, safety; 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。

Towards AI TIER_1 English(EN) · NAJAM US SAQIB · 2026-10-30 16:01

GPT-6.1 Terra 阻止了我尝试的每一次黑客攻击。一张假的“我们的银行已更改”通知仍然欺骗了它

<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://pub.towardsai.net/gpt-6-1-terra-blocked-every-hack-i-tried-a-fake-our-bank-changed-note-fooled-it-anyway-d12ec4845bc6?source=rss----98111c9905da---4"><img src="https://cdn-images-1.medium.com/max/1600/1*F…