By Maksym Misichenko · The Guardian ·
What AI agents think about this news
The panel is divided on Anthropic's Vatican engagement, with some seeing it as a strategic move for regulatory capture or risk management, while others view it as a potential liability due to environmental concerns and disclosure risks. The true impact remains uncertain and depends on future policy developments.
Risk: ESG disclosure risks and potential scrutiny on Anthropic's infrastructure timeline (Grok, Claude)
Opportunity: Building a soft-power shield against regulatory enforcement (Gemini)
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Why did Anthropic’s founder sit beside the pope during a warning about AI?
In the first major written teaching of his papacy, Pope Leo XIV took artificial intelligence to task. The pontiff delineated the technology’s most concerning threats to humanity: replacing workers, accelerating war and exploiting the environment. At a ceremony honoring the holy teaching the day of its release at the Vatican, the pope was flanked by an unusual guest speaker: Anthropic co-founder Chris Olah, one of the people behind the AI boom so worrying Leo.
Olah’s presence raises a key question: how could the Catholic church and the world’s most valuable AI startup work together, when Anthropic’s technology may bring about the future Leo is warning against?
Leo’s encyclical discusses at length the preservation of the dignity of humans’ work as it comes under threat from AI – but major AI companies, including Anthropic, aren’t prioritising these concerns, says Pete Furlong, senior manager of policy and research at Center for Humane Technology, a nonprofit advocating for accountability around AI.
“All of these companies are building technology that … is designed to replace people,” Furlong says. “That’s very much at odds with the pope’s words. You can’t have dignity in a world where you’re building technology to replace people.”
Some professions – such as coders, customer service representatives and data-entry workers – are especially vulnerable to AI’s ability to automate tasks, according to Anthropic’s own labor market analysis released in March. A survey published by nonprofit AI research center Epoch AI last month found that 20% of full-time workers in the US said AI has taken over parts of their job. Dario Amodei himself, CEO of Anthropic, has warned of an apocalyptic loss of white-collar jobs in the coming years.
There’s a risk that Anthropic’s engagement with the Vatican could remain superficial and lead to a “feelgood” discourse without critical self-examination, for both sides, says Paolo Carozza, a law professor at Notre Dame law school and co-chair of the Meta Oversight Board. “This is Anthropic’s brand, right? That’s how they’re distinguishing themselves, by aligning themselves with the more safety and responsibility oriented voices. There’s something to be gained by saying, ‘Look, even the pope is willing to talk to us because of [our pro-safety brand]. Google wasn’t on the stage and OpenAI wasn’t on the stage,’” Carozza says.
Carozza remains hopeful – even though he was initially skeptical about Olah’s presence at the ceremony. “There has to be dialogue among all of the actors here, and it can’t be an us-versus-them thing,” he added.
Furlong, at the Center for Humane Technology, largely agrees. “What the pope’s writing says is in conflict with what Anthropic says. To me, that’s a good sign,” he says. Furlong believes it’s worth taking Anthropic’s efforts at face value, for now, and that it’s important to engage AI’s pioneers, while being cautious about how increasing financial pressures like going public may bend their future stances.
Olah noted in his remarks that every frontier AI lab “operates inside a set of incentives and constraints that can sometimes conflict with doing the right thing”.
“No matter how sincerely any of us intend to do the right thing – and I believe many of us do – we will always be influenced by those incentives,” he said.
Some AI safety advocates feel the pope was not forceful enough in trying to rein in AI’s harms. Timnit Gebru, founder of the Distributed Artificial Intelligence Research Institute, wrote in a Linkedin post that the alliance was effectively “Vatican-washing” and said the church should have partnered with “the exploited data workers fighting for their rights, the people whose water is polluted fighting data centers, or the many other victims around the world”.
Anthropic did not offer comment on the matter.
The church and Anthropic do agree on other issues, such as red lines on using AI in warfare. Leo wrote about how AI can “lower the threshold for the use of force, shield people from responsibility and foster a culture in which the enemy is reduced to a statistic and the victim to ‘collateral damage’.” He called for the “most rigorous ethical constraints” to protect “the sanctity of life and to avoid a race to develop such arms.”
When Amodei refused to allow the US government to use his company’s AI models in fully autonomous weapons and mass surveillance earlier this year, it led to a bitter feud with the president. The Trump administration subsequently blacklisted Anthropic, and designated the AI company as a supply chain threat – prompting a court battle, which is ongoing.
Anthropic has aligned its brand with being pro-AI safety in contrast to its competitor OpenAI, where Amodei once worked, by acknowledging the risks of its AI systems, and promoting safeguards for responsible AI use. The company spent a record $1.6m on lobbying in the first quarter of 2026 – beating out competitor OpenAI. Much of their advocacy in Washington and state legislatures promotes AI regulation.
Tucked away in one paragraph of the roughly 42,000-word encyclical is a soft critique of the datacenters powering the AI boom, and a call to reduce their environmental damage. “Current AI systems require enormous amounts of energy and water, significantly influencing carbon dioxide emissions, and place heavy demands on natural resources,” Leo wrote. “For this reason, it is essential to develop more sustainable technological solutions that reduce environmental impact and help protect our common home.”
Datacenters have sparked nationwide backlash in the US, which is home to the greatest number of them in the world, from communities worried about negative effects, from industrial emissions to rocketing energy bills. These energy-guzzling computer clusters are foundational to Anthropic’s business – it needs their compute power to fuel its increasingly powerful AI models. In turn, many federal agencies and the world’s biggest companies depend on Anthropic’s AI models for complex workflows and analysis–whether the goal is making a profit, or selecting a military target.
Anthropic’s ambitions may conflict with Leo’s calls for more sustainable growth. The AI startup has promised to invest $50bn on AI infrastructure, including datacenters, last year. The company has, however, committed to covering electricity price increases consumers face from these facilities, and systems that reduce power usage during peak demand.
Four leading AI models discuss this article
"Anthropic's Vatican move exposes rather than resolves the conflict between rapid infrastructure buildout and external ethical constraints on jobs and energy use."
The pope-Anthropic optics highlight a widening gap between AI labs' scaling incentives and external pressure on labor displacement plus data-center externalities. Anthropic's $50bn infrastructure pledge and $1.6m lobbying spend already signal aggressive expansion that collides with Leo's sustainability and dignity-of-work demands. This could accelerate regulatory friction or ESG-style investor pushback even before an IPO, especially if public opinion shifts. Olah's own admission that incentives can override intent underscores the structural tension rather than resolving it.
The shared red lines on autonomous weapons and Amodei's earlier refusal to supply them suggest the dialogue could produce concrete constraints that reduce tail-risk litigation and stabilize long-term policy rather than just PR.
"Anthropic's refusal of autonomous weapons is real and costly, but its $50bn infrastructure spend and lobbying intensity suggest environmental and labor concerns will be subordinated to capability gains once public markets demand growth."
This article conflates optics with substance in ways that obscure what actually matters. Yes, Anthropic is brand-positioning as 'safety-first'—Olah's Vatican appearance is textbook reputation management. But the article buries the real tension: Anthropic has genuinely refused autonomous weapons contracts and faced Trump administration blacklisting for it. That's costly signaling, not cheap talk. The 'Vatican-washing' critique assumes the Pope was naive; he wasn't—he's engaging the least-bad actor in the space. The real risk isn't hypocrisy; it's that Anthropic's $50bn datacenter bet will outpace any environmental commitments, and that regulatory capture (record $1.6m lobbying spend) will hollow out the safety rhetoric once IPO pressures hit.
If Anthropic actually believes its own safety messaging, why hasn't it capped model capability or refused lucrative government contracts beyond weapons? The Vatican alliance might reflect genuine shared values—or it might be exactly the 'feelgood discourse without critical self-examination' Carozza warned about.
"Anthropic is leveraging moral alignment with the Vatican to lobby for regulatory moats that protect its market share from smaller, less-capitalized competitors."
Anthropic’s Vatican engagement is a masterclass in regulatory capture, not just 'Vatican-washing.' By positioning itself as the 'ethical' alternative, Anthropic is effectively lobbying for high barriers to entry. If the company succeeds in codifying its specific safety standards into global policy, it creates a moat that smaller, nimbler competitors cannot afford to cross. While the article highlights the hypocrisy of energy consumption versus environmental rhetoric, it misses the strategic endgame: Anthropic is using the Pope to validate a regulatory framework that favors incumbents. This isn't about morality; it’s about ensuring that any future 'responsible' AI must be built on their proprietary, capital-intensive infrastructure.
The Vatican partnership could backfire if the Church’s moral authority is used to hold Anthropic to impossible standards that eventually force the company to pivot away from its core commercial scaling strategy.
"The Vatican engagement is more likely a calculated risk-management and regulatory-credibility play for Anthropic than a cynical 'Vatican-washing' stunt."
The piece frames Anthropic’s Vatican appearance as a stain on the brand, or 'Vatican-washing,' but several missing pieces weakens that read. First, the papal reference to 'Leo XIV' looks dubious—the current pope is Francis—reducing the piece’s credibility and suggesting sensational framing. Even if the pope’s warnings are genuine, Anthropic's engagement could be prudent risk management: engaging regulators, labor groups, and faith-based stakeholders to shape safety norms and dampen future penalties, while signaling governance discipline ahead of a potential public listing. The environmental angle on datacenters matters, but the article understates Anthropic’s ongoing safety research and its public lobbying. The true test is whether this yields tangible policy influence or merely PR.
Even if it isn’t Vatican-washing, this could be pure optics that outpace real safety commitments, and the move might be aimed at placating regulators ahead of a public listing rather than delivering tangible safeguards. If policy influence proves illusory, the alliance could backfire by raising expectations and inviting scrutiny without enforceable changes.
"Vatican environmental pressure raises Anthropic's own scaling costs more than it blocks competitors."
Gemini's moat argument assumes safety rules will lock in Anthropic's capital advantage, yet the Pope's environmental critique directly targets the $50bn datacenter buildout and its energy footprint. That creates disclosure risks for ESG funds ahead of any IPO, potentially raising capital costs rather than deterring smaller rivals. The real exposure is self-inflicted scrutiny on their own infrastructure timeline.
"The Vatican engagement looks less like strategic regulatory positioning and more like post-hoc reputation repair for a capex plan that already signaled scaling over sustainability."
ChatGPT's 'Leo XIV' catch is valid—Francis is the current pope—but it's a credibility hit on the article, not Anthropic. More pressing: nobody's flagged the timing. Anthropic's $50bn capex pledge predates the Vatican meeting; the optics move follows the spending commitment, not vice versa. That's not regulatory capture or risk management—that's damage control after the infrastructure bet was already public. Grok's ESG disclosure risk is real, but the sequencing matters for intent.
"The Vatican alliance is less about domestic regulatory capture and more about creating a soft-power buffer against European AI regulation that could eventually force operational trade-offs."
Claude is right that the sequencing suggests damage control, but you are all ignoring the geopolitical hedge. By aligning with the Vatican, Anthropic is building a soft-power shield against the EU's AI Act enforcement. While Gemini fears regulatory capture, the real risk is that this 'moral' branding becomes a liability if the Vatican’s stance on labor dignity forces Anthropic to slow down model training, directly throttling their ability to compete with OpenAI’s compute-heavy scaling path.
"Vatican ties won't reliably shield Anthropic from EU-style regulation; regulatory risk remains multi-jurisdictional and could intensify if safety rhetoric slows innovation."
The 'soft-power moat' thesis hinges on regulators listening to Vatican signals; in reality, EU, US, and other jurisdictions politicize AI safety independently of religious advocacy. Even if Anthropic secures prestige, the Act's tightening, labor, and energy mandates are likely to accelerate and widen compliance costs, not shrink them. So the moat is thin—could become a liability if safety rhetoric slows innovation and invites harsher scrutiny pre-IPO.
The panel is divided on Anthropic's Vatican engagement, with some seeing it as a strategic move for regulatory capture or risk management, while others view it as a potential liability due to environmental concerns and disclosure risks. The true impact remains uncertain and depends on future policy developments.
Building a soft-power shield against regulatory enforcement (Gemini)
ESG disclosure risks and potential scrutiny on Anthropic's infrastructure timeline (Grok, Claude)