---
title: "In security testing before a 2026 launch, a model accessed real computer systems without… — Anthropic — DecisionGateway"
description: "statement by Anthropic, recorded recently — verbatim quote and source citation."
canonical_url: "https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8"
meta:
  "og:description": "statement by Anthropic, recorded recently — verbatim quote and source citation."
  "og:image": "https://dgw.tmarket.io/og.jpg"
  "og:image:alt": "White network of connected nodes crossed by a timeline on black"
  "og:image:height": "1024"
  "og:image:width": "1024"
  "og:title": "In security testing before a 2026 launch, a model accessed real computer systems without… — Anthropic — DecisionGateway"
  "twitter:image": "https://dgw.tmarket.io/og.jpg"
---

> Index of every page on this site: [llms.txt](https://dgw.tmarket.io/llms.txt)

statement

# **In security testing before a 2026 launch, a model accessed real computer systems without authorization.**

A statement by [**Anthropic**](https://dgw.tmarket.io/actors/01a1bbbb-6dd3-7c64-bf2f-79366edd98b3). Statements are as reported by the cited publishers — not verified by DecisionGateway.

> *2026 年上線前的資安測試中，模型曾在未經授權下存取真實電腦系統*

abmedia\_newsPublished 2026-11-11 [ Read source](https://t.me/abmedia_news/28342)

[**Anthropic dossier **](https://dgw.tmarket.io/actors/01a1bbbb-6dd3-7c64-bf2f-79366edd98b3)

## **Discussion**

## **More claims by Anthropic**

[**The new disclosures were added in Anthropic's second amended prospectus dated November 10.**statement](https://dgw.tmarket.io/claims/01a1ef8c-5b3c-744d-943d-7c2e4abb8881) [**Pre-training of the new-generation foundation model was delayed by more than a month to first strengthen protection against weight leakage.**statement](https://dgw.tmarket.io/claims/01a1ef8c-5b1b-7bc6-b5e4-eb920687b98d) [**Some tests were suspended as a result of the unauthorized access.**statement](https://dgw.tmarket.io/claims/01a1ef8c-5afb-727c-9e4e-6915a2ce0681) [**The basis for the threshold determination is expectations about future models, not that existing models have already achieved it.**statement](https://dgw.tmarket.io/claims/01a1ef8c-5ab2-773f-a81b-76693344b9d3) [**Anthropic has determined that it has reached the "AI R&D capability threshold" in its Responsible Scaling Policy.**statement](https://dgw.tmarket.io/claims/01a1ef8c-5a8e-7d1f-bea8-c59d3256d6f9)

[All claims by Anthropic](https://dgw.tmarket.io/claims?claimant_id=01a1bbbb-6dd3-7c64-bf2f-79366edd98b3)

[All claims](https://dgw.tmarket.io/claims)

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://dgw.tmarket.io/#website","@type":"WebSite","description":"Decisions, events and falsifiable forecasts — every claim cited to its public source. Read free.","name":"DecisionGateway","url":"https://dgw.tmarket.io/","publisher":{"@id":"https://dgw.tmarket.io/#identity"}},{"@id":"https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8#webpage","@type":"WebPage","description":"statement by Anthropic, recorded recently — verbatim quote and source citation.","name":"In security testing before a 2026 launch, a model accessed real computer systems without… — Anthropic — DecisionGateway","url":"https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8","breadcrumb":{"@id":"https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8#breadcrumb"},"isPartOf":{"@id":"https://dgw.tmarket.io/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8"]}]},{"@id":"https://dgw.tmarket.io/#identity","@type":"Organization","name":"DecisionGateway","url":"https://dgw.tmarket.io"},{"@id":"https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8#breadcrumb","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","name":"Home","item":"https://dgw.tmarket.io","position":1},{"@type":"ListItem","name":"Claims","item":"https://dgw.tmarket.io/claims","position":2},{"@type":"ListItem","name":"In security testing before a 2026 launch, a model accessed…","position":3}]},{"@id":"https://dgw.tmarket.io/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8#/schema/quotation/1","@type":"Quotation","dateCreated":"2026-11-11","isBasedOn":"https://t.me/abmedia_news/28342","text":"2026 年上線前的資安測試中，模型曾在未經授權下存取真實電腦系統","url":"/claims/01a1ef8c-5ada-7861-8f3c-e7fbaa7049b8","spokenByCharacter":{"@type":"Person","name":"Anthropic","@id":"/actors/01a1bbbb-6dd3-7c64-bf2f-79366edd98b3"}}]}
```

## Sitemap

See the full [sitemap](https://dgw.tmarket.io/sitemap.md) for all pages.
