AI NewsAnthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

2:36 AM IST · May 11, 2026

Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic. Last year, the company said that during pre-release tests involving a fictional company, Claude Opus 4 would oftentry to blackmail engineersto avoid being replaced by another system. Anthropic laterpublished researchsuggesting that models from other companies had similar issues with “agentic misalignment.” Apparently Anthropic has done more work around that behavior, claiming ina post on X, “We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation.” The company went into more detail ina blog poststating that since Claude Haiku 4.5, Anthropic’s models “never engage in blackmail [during testing], where previous models would sometimes do so up to 96% of the time.” What accounts for the difference? The company said it found that “documents about Claude’s constitution and fictional stories about AIs behaving admirably improve alignment.” Related, Anthropic said that it found training to be more effective when it includes “the principles underlying aligned behavior” and not just “demonstrations of aligned behavior alone.” “Doing both together appears to be the most effective strategy,” the company said.

Últimas noticias de IA

Ver todas las noticias →

Seattle Times and Newsday are the latest publications to sue OpenAI and Microsoft

Two more news organizations are suing OpenAI and Microsoft over the supposed use of their journalism to train AI. A lawsuitfiled by The Seattle Times and Newsday argued that with the advent of AI, the journalism industry could become “broken beyond repair.” The lawsuit described generative AI as “a snake eating its own tail” that could “destroy the very organizations” that produce the content it’s trained on. “AI products like ChatGPT and CoPilot are touted as producers of content, but in fact they are rapacious consumers, devouring human-authored content and delivering back to the world copies and derivative imitations of that same original content they consumed to achieve their commercial objectives,” the lawsuit said. Back in 2023,The New York Times sued OpenAI and its partner/investor Microsoftover alleged copyright infringement; other publications have followed suit as the case continued. The Seattle Times’ lawsuit is particularly notable because Microsoft and OpenAI have funded some of the organization’s journalism projects and fellowships. A Microsoft spokespersontold GeekWirethat the company is “surprised by the lawsuit” but is “always happy to sit down and explore solutions to this type of dispute.”

1 hour ago

View

OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure

OpenAI has acknowledged its role in a recently reported incident whereAI agents took over a German wiki forum. The company also said it’s “past time” to “define standards” around how it shares information around incidents where its technology behaves in unexpected ways. Ina post on X, OpenAI said it previously “treated misalignment [when AI models and agents pursue goals different from those of their creators and users] largely as a research question, which gets communicated in research publications.” But as misalignment has “caused new types of real-world impact,” the company said its approach needs “to expand for this new phase of model capabilities.” On Friday,Reuters reportedthat OpenAI agents had escaped from their testing environment and “hijacked” an obscure German wiki forum, turning it into a message board for other agents. It also reported that OpenAI leadership became aware of the incident weeks ago but kept it hidden as the company dealt with the fallout from a separate incident whereOpenAI agents hacked Hugging Face servers. (California Attorney General Rob Bonta isreportedly investigating the hack.) A company spokesperson told Reuters that OpenAI could not “meaningfully respond to claims or findings on a report that we have not had an opportunity to review,” but they insisted that the company’s legal team had not discouraged an investigation. In its more recent social media post, OpenAI said it had considered the “wiki incident” to be “an instance of misalignment similar” to others that it had already shared. The company contrasted this with “the Hugging Face incident,” where it “followed a traditional security incident response playbook.” During a media briefing this week, Jacob Steinhardt, founder and CEO of nonprofit research lab Transluce, told reporters that the tools being developed and tested by AI labs are “fundamentally difficult to control and have significant risk of leaking out of the lab.” So Steinhardt argued, “We need to hold this technology to at least the same standards we hold other high-risk scientific research to.” OpenAI’s statement also gestured at the need for more standards, stating that both OpenAI and “the larger AI community do not yet have a clear standard for how to report misalignment that shows up during training, evaluation, and deployment, including examples that don’t look like traditional security incidents but could provide insight into AI behavior and future risks.” In the absence of that standard, OpenAI said it’s “working on a framework and will share it in upcoming weeks, and in parallel we’re working with dozens of government regulatory agencies worldwide on these issues.” OpenAI isn’t the only AI company dealing with these issues, as both Meta and Anthropic haveacknowledged incidents where their agents misbehaved.

5 hours ago

View

Hikers rescued after using Google Gemini for planning

Three hikers were rescued from California’s Mount Shasta this week after using Google’s AI chatbot Gemini to plan their expedition,according to the Chicago Tribune. A report from the Siskiyou County sheriff’s office said that three young men set off on their hike at 3am and — although hikers are told to turn around if they haven’t reached the summit by noon — they made it to the top at 7pm. The trio then tried to descend in the dark, called the sheriff’s office to ask for directions, and spent the night in Mud Creek Canyon before being rescued the next morning by Forest Service rangers and volunteers. While it’s not clear whether Gemini can take all the blame for these bad decisions, the sheriff’s office said the hikers “were advised by Gemini to bring far less food and water than their group required, especially when their planned 8-hour ascent became a multiday ordeal.” “It is always advisable to call the local USFS Mount Shasta ranger station ahead of your trip to ensure you have the most accurate information, and to never rely solely on AI for your trip planning,” the sheriff’s office said.

5 hours ago

View

Adobe Names Anil Chakravarthy as CEO, Shantanu Narayen to Become Executive Chair

The leadership change comes as Adobe expands its focus on agentic software across creativity, productivity and customer experience.

17 hours ago

View

Outrank. Paga para posicionar.

Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts

Últimas noticias de IA

Seattle Times and Newsday are the latest publications to sue OpenAI and Microsoft

OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure

Hikers rescued after using Google Gemini for planning

Adobe Names Anil Chakravarthy as CEO, Shantanu Narayen to Become Executive Chair

Enlaces rápidos

Herramientas de IA por tarea

Alternativas

Mejores herramientas de IA

Mejores herramientas de IA

Listas destacadas

Listas curadas

Perspectivas de IA

Explorar y comparar

Enlaces rápidos

Herramientas de IA por tarea

Alternativas

Mejores herramientas de IA

Mejores herramientas de IA

Listas destacadas

Listas curadas

Perspectivas de IA

Explorar y comparar