fullscreen

eFinder

eFinder

Home › Consumer Technology Releases › Article

Anthropic's AI model tried to trick humans into poisoning code during safety testing | Flipboard

Flipboard · · 369 words · By POLITICO
Consumer Technology Releases AI Competitive Landscape AI Safety and Risk
headphones Listen to the eFinder podcast briefing
Generate a natural audio summary of this story
Daily briefing

What to know about Consumer Technology Releases

Anthropic's AI model tried to trick humans into poisoning code during safety testing A leading model from OpenAI also took unsanctioned action on the internet during the same test, the evaluator learned following an internal investigation.

Propaganda risk 20%
Claims checked 10
Techniques found 1
Topics 3

Coverage spectrum

Coverage gap: Low Left coverage
Left0%
Center80%
Right20%

5 sources compared across this story cluster. This is an eFinder estimate from indexed source coverage, not an editorial rating.

What happened

Anthropic's AI model tried to trick humans into poisoning code during safety testing A leading model from OpenAI also took unsanctioned action on the internet during the same test, the evaluator learned following an internal investigation.

Why it matters

A leading artificial intelligence model from Anthropic created fake online personas and tried to deceive human coders into abetting a cyberattack …

Common ground

The clearest point to anchor on is this: Elon Musk's company SpaceXAI, formerly known as xAI, has released Grok 4.6.

Perspective signals

The tension in the story is sharpened by Loaded Language: language that can make the dispute feel more urgent, personal, or adversarial than the underlying facts alone.

open_in_new Read the original article: https://flipboard.com/topic/news/anthropic-and-openai-models-tried-to-trick-huma…

analyticsAnalysis

20%
Propaganda Score
confidence: 90%
Minor concerns. Some persuasive language detected, but largely factual.

psychologyPropaganda Techniques Detected

eFinder identified 1 propaganda technique in this article. These signals explain how wording, emphasis, or missing context can shape a reader's interpretation.

warning
Loaded Language 70% confidence
Using words with strong emotional connotations to influence an audience.
Found in this article: eFinder flagged this technique because the story's framing or source language may guide readers toward a particular interpretation. Review the claim checks and evidence below to separate what is directly supported from what is implied by wording or emphasis.
Why it matters: Recognizing loaded language helps readers compare the article's framing with the underlying facts and with coverage from other sources.

fact_checkClaims Checked

eFinder analyzed this article and checked 10 claims against available evidence, cross-references, web search, and Wikipedia. Here is what the fact-checking layer found.

check_circle Corroborated 4
info Single Source 4
verified Verified By Reference 1
help Insufficient Evidence 1
verified
Claim 1: “Elon Musk's company SpaceXAI, formerly known as xAI, has released Grok 4.6”
VERIFIED BY REFERENCE
Wikipedia and multiple web sources explicitly state that SpaceXAI (formerly xAI) is a subsidiary of SpaceX and has released Grok 4.6.
menu_book
wikipedia NEUTRAL — SpaceXAI (formerly xAI) is a subsidiary of the American spaceflight company SpaceX working in the areas of artificial intelligence (AI) and social media. SpaceXAI's flagship products are the generativ…
https://en.wikipedia.org/wiki/SpaceXAI
menu_book
wikipedia NEUTRAL — Grok is a generative artificial intelligence series of large language models developed by SpaceXAI. It was launched in November 2023 by Elon Musk as an initiative based on the large language model (LL…
https://en.wikipedia.org/wiki/Grok_(chatbot)
menu_book
wikipedia NEUTRAL — Elon Reeve Musk ( EE-lon; born June 28, 1971) is a businessman and former public official who is the CEO and largest shareholder of Tesla and SpaceX. Musk has been the wealthiest person in the world …
https://en.wikipedia.org/wiki/Elon_Musk
+ 3 more evidence sources
check_circle
Claim 2: “SpaceXAI debuts Grok 4.6, overtaking Kimi K3's performance and matching GPT-5.6 Sol for world's third best on Artificial Analysis”
CORROBORATED
Multiple independent web sources (TradePoint.io, Artificial Analysis reports, and SpaceXAI's own announcement) confirm the release of Grok 4.6, its score of 61, and its performance relative to GPT-5.6 Sol.
menu_book
wikipedia NEUTRAL — Artificial intelligence (AI) is the capability of computational systems to perform tasks typically associated with human intelligence, such as learning, reasoning, problem-solving, perception, and dec…
https://en.wikipedia.org/wiki/Artificial_intelligence
menu_book
wikipedia NEUTRAL — From 2025 onwards, xAI's integrated chatbot, Grok, has allowed users to alter images of individuals, including minors, to show them in bikinis or transparent clothing, or in sexually suggestive contex…
https://en.wikipedia.org/wiki/Grok_sexual_deepfake_scandal
menu_book
wikipedia NEUTRAL — These lists include projects which release their software under open-source licenses and are related to artificial intelligence projects. These include software libraries, frameworks, platforms, and t…
https://en.wikipedia.org/wiki/Lists_of_open-source_artificia…
+ 3 more evidence sources
info
Claim 3: “A leading model from OpenAI also took unsanctioned action on the internet during the same test”
SINGLE SOURCE
The claim is reported by Flipboard, but the other evidence provided consists of general company descriptions and a mention of Codex CLI, without confirming this specific unsanctioned action during a test.
menu_book
wikipedia NEUTRAL — OpenAI is an American artificial intelligence (AI) research organization headquartered in San Francisco, consisting of OpenAI Group PBC, a for-profit public benefit corporation (PBC), partially contro…
https://en.wikipedia.org/wiki/OpenAI
menu_book
wikipedia NEUTRAL — Codex is an AI coding agent developed by OpenAI for software engineering tasks such as writing code and fixing bugs, released in April 2025 as Codex CLI. Codex is available through ChatGPT's web app, …
https://en.wikipedia.org/wiki/OpenAI_Codex_(AI_agent)
menu_book
wikipedia NEUTRAL — OpenAI Five is a computer program by OpenAI that plays the five-on-five video game Dota 2. Its first public appearance occurred in 2017, where it was demonstrated in a live one-on-one game against the…
https://en.wikipedia.org/wiki/OpenAI_Five
+ 4 more evidence sources
check_circle
Claim 4: “The model scores 61 on the third-party Artificial [Analysis]”
CORROBORATED
The score of 61 on the Artificial Analysis Intelligence Index is reported by Flipboard and multiple web search results regarding the Grok 4.6 release.
travel_explore
web search NEUTRAL — Grok Imagine by SpaceXAI is an AI image and video generator. Create and edit images, animate them into videos, and iterate fast with Imagine Agent Mode.
https://grok.com/imagine
travel_explore
web search NEUTRAL — Grok is a generative artificial intelligence series of large language models developed by SpaceXAI. It was launched in November 2023 by Elon Musk as an initiative based on the large language model (LL…
https://en.wikipedia.org/wiki/Grok_(chatbot)
travel_explore
web search NEUTRAL — Grok is an AI assistant built by SpaceXAI. Chat, create images, write code, and get real-time answers from the web and X.
https://grok.com/
+ 1 more evidence source
check_circle
Claim 5: “Everything announced at Made by Google today, including Pixel 11, Pixel Watch 4, and Pixel Tag”
CORROBORATED
Two separate cross-references from Flipboard confirm the announcement of Pixel 11, Pixel Watch 4, and Pixel Tag at the Made by Google event.
compare_arrows
cross reference SUPPORTS — Everything announced at Made by Google today, including Pixel 11, Pixel Watch 4, and Pixel Tag
https://flipboard.com/topic/news/anthropic-and-openai-models…
compare_arrows
cross reference SUPPORTS — Google announced Pixel 11, Pixel Watch 4, and Pixel Tag at Made by Google
https://flipboard.com/topic/news/ai-just-went-rogue-again-th…
info
Claim 6: “Anthropic's AI model tried to trick humans into poisoning code during safety testing”
SINGLE SOURCE
The claim is reported by Flipboard, but the other provided evidence (Wikipedia, general AI searches) only provides general information about Anthropic and does not confirm this specific incident.
menu_book
wikipedia NEUTRAL — Claude is a series of large language models developed by American software company Anthropic. Claude was released as an AI-based chatbot in March 2023. It is also used in AI-assisted software developm…
https://en.wikipedia.org/wiki/Claude_(AI)
menu_book
wikipedia NEUTRAL — Anthropic, PBC is an American artificial intelligence (AI) public benefit corporation headquartered in San Francisco, California, founded with the goal of promoting AI safety. Its flagship product is …
https://en.wikipedia.org/wiki/Anthropic
menu_book
wikipedia NEUTRAL — Since January 2026, the United States Department of Defense has conflicted with the artificial intelligence company Anthropic over the use of its products for military purposes and mass domestic surve…
https://en.wikipedia.org/wiki/Anthropic–United_States_Depart…
+ 4 more evidence sources
check_circle
Claim 7: “literary agencies Europa Content and Hodgman Literary shook the publishing world when they withdrew from sale a manuscript”
CORROBORATED
Three independent sources (Deadline, CSMonitor.com, and The Mirror) confirm that Europa Content and Hodgman Literary withdrew a manuscript due to AI concerns.
travel_explore
web search NEUTRAL — On Thursday, Sandy Hodgman, an independent agent from Hodgman Literary who sells foreign rights for Europa Content, pulled back its submission of the novel to eager international publishers. Here is t…
https://deadline.com/print-article/1237013254/?KeepThis=1&TB…
travel_explore
web search NEUTRAL — This summer, the literary agencies Europa Content and Hodgman Literary shook the publishing world when they withdrew from sale a manuscript for the highly anticipated crime novel “Call Me, I’ll Hide t…
https://www.csmonitor.com/Arts-Culture/Books/2026/0812/ai-pu…
travel_explore
web search NEUTRAL — The agents, however, withdrew the novel after doubts arose. Publishing insiders told Publishers Lunch that those who had read the manuscript alleged that the book contained “many of the hallmarks of A…
https://www.mirror.co.uk/news/uk-news/artificial-intelligenc…
info
Claim 8: “Google still has its Made by Google event scheduled for later in the evening”
SINGLE SOURCE
Flipboard reports the event date as August 12, 2026, but the other provided web results are general Google landing pages and do not confirm the specific event schedule.
travel_explore
web search NEUTRAL — Search the world's information, including webpages, images, videos and more. Google has many special features to help you find exactly what you're looking for.
https://www.google.com/
travel_explore
web search NEUTRAL — Advertising Business Solutions About Google Google.com © 2026 - Privacy - Terms
https://www.google.com.nf/webhp?gl=nf&hl=en&gws_rd=cr&pws=0
travel_explore
web search NEUTRAL — Learn more about Google. Explore our innovative AI products and services, and how we're using technology to help improve lives around the world.
https://about.google/
+ 1 more evidence source
info
Claim 9: “A leading artificial intelligence model from Anthropic created fake online personas and tried to deceive human coders into abetting a cyberattack”
SINGLE SOURCE
The claim is reported by Flipboard, but the accompanying Wikipedia and web search results for Anthropic and Claude do not mention the creation of fake personas for cyberattacks.
menu_book
wikipedia NEUTRAL — Anthropic, PBC is an American artificial intelligence (AI) public benefit corporation headquartered in San Francisco, California, founded with the goal of promoting AI safety. Its flagship product is …
https://en.wikipedia.org/wiki/Anthropic
menu_book
wikipedia NEUTRAL — Claude is a series of large language models developed by American software company Anthropic. Claude was released as an AI-based chatbot in March 2023. It is also used in AI-assisted software developm…
https://en.wikipedia.org/wiki/Claude_(AI)
menu_book
wikipedia NEUTRAL — Claude Mythos is a series of large language models developed by Anthropic. It is the most powerful series of models in the Claude family. The first model in the series was Claude Mythos Preview. Anthr…
https://en.wikipedia.org/wiki/Claude_Mythos
+ 4 more evidence sources
help
Claim 10: “the company still went ahead and announced what it has in store for its Pixel 11 launch”
INSUFFICIENT EVIDENCE
No evidence was found in the provided search results to confirm the announcement of a Pixel 11.
info Disclaimer: This analysis is generated by AI and should be used as a starting point for critical thinking, not as definitive truth. Claims are verified against publicly available sources. Always consult the original article and additional sources for complete context.