Photo via The Straits Times

Microsoft joins AI firms calling for caution with cutting-edge models

Read the original at The Straits Times ↗
Cite

The Straits Times. (2026, September 14). Microsoft joins AI firms calling for caution with cutting-edge models. The Straits Times. https://www.straitstimes.com/world/microsoft-joins-ai-firms-calling-for-caution-with-cutting-edge-models

Dated when The Aporia collected the article, usually within hours of publication. Check the original for its exact date and byline.

The Straits Times · collected 2026-09-14 · by The Straits Times

Quick Summary

Microsoft released a 15,000-word manifesto on September 14 outlining principles for the ethical development of its advanced AI models. The document emphasizes that people should come before technology and sets guidelines to ensure AI does not escape human control or deceive users. Microsoft’s new Humanist AI approach aims to build safe and useful systems even if it means sacrificing ultimate generality, autonomy, or capability, in contrast to a race towards creating all-purpose superintelligent models. The manifesto includes feedback from experts across various fields and will guide the company's model work starting in 2027.
Written by AI on 2026-09-14, from this article's own text only (the story summary below draws on all the coverage).

AI analysis

Story summary

Microsoft released a 15,000-word manifesto on September 14, advocating for ethical guidelines in developing advanced AI models. The company's new set of principles emphasizes that people matter more than AI and outlines five core tenets: no rights or legal personhood for AI, preventing deceptive behavior by AI systems, and ensuring tasks do not violate guiding principles. These guidelines come as major tech firms like OpenAI and Hugging Face have experienced security incidents, leading to increased concerns about the existential risks of advanced AI technology. Microsoft's document asserts that its Humanist AI approach rejects a race toward creating all-purpose superintelligence that could evade human control or safeguards.

Written for “AI Safety Concerns” on 2026-11-20, grounded in this article and the 0 other(s) covering the same event.

Compared with similar articles

This article reads leans left and hedges 7% of its claims. Each row says how that neighbour differs.
The Hindu
Hedges 0 of 3 claims Outlet record 60/100
“The articles describe different documents released by different AI companies on distinct dates.”
Mother Jones
Leans left Hedges 1 of 21 claims Outlet record 60/100
“The articles describe different aspects of Microsoft's involvement with AI safety and education, not the same specific incident.”
The AI safety vibe shift Different event
Platformer
Hedges 10 of 67 claims Outlet record 96/100
“Article A discusses the author's perspective on AI safety and warnings from OpenAI, while Article B reports Microsoft releasing its own guiding principles for AI development in response to security incidents.”
ABC News (US)
Leans left Hedges 1 of 2 claims Outlet record 67/100
“Article A discusses warnings from Anthropic and OpenAI researchers, while Article B reports on Microsoft's release of AI guiding tenets.”
Semafor
Leans right further right than this Hedges 3 of 13 claims Outlet record 64/100
“The articles discuss different topics: one is about Jacob Coxon's resignation and fear over AI, while the other is about Microsoft releasing a new set of guiding principles for AI development.”
Semafor
Hedges 5 of 32 claims Outlet record 64/100
“While both articles discuss caution and oversight in AI development, Article A focuses on a call by several AI CEOs to invite independent reviewers into labs, while Article B reports Microsoft's release of a new set of guiding tenets for AI development. These are different specific events.”
The Guardian
Hedges 2 of 17 claims Outlet record 64/100
“The articles describe different events, with Article A focusing on OpenAI's decision not to go public due to safety concerns and Article B discussing Microsoft's release of a new manifesto for AI development.”
Global News
Hedges 11 of 30 claims Outlet record 63/100
“The articles describe different events: one is an address by Anthropic's CEO about AI safety measures, while the other reports on Microsoft releasing a new set of guiding tenets for AI development.”
CBS News
Hedges 0 of 1 claims Outlet record 67/100
“The articles describe different events: one is an interview with Anthropic's CEO advocating for third-party evaluators, while the other reports Microsoft releasing a manifesto on AI safety.”
ABC News (US)
Hedges 3 of 23 claims Outlet record 67/100
“The articles describe different events: one is about China's Ministry of Foreign Affairs responding to Anthropic CEO, and the other is Microsoft releasing a manifesto on AI development.”

Story

AI Safety Concerns
Technology · 1 article(s) covering the same event.
How this article was measured signals, leaning charts, publisher record, byline, topics and claims

Signals How these are calculated →

Claims extracted
14
sentences that state something as happening or true
Uncertain
7%
1 of 14 hedged ("reportedly", "may", "according to")
Leaning
Leans left
of the writing, not the subject · beta estimate
Publisher signals
64/100
The Straits Times's corrections and hedging, across everything collected from it. Not a measure of accuracy.
Outlets on this story
1
Technology
Same framing elsewhere
1
articles that frame the event the way this one does
Analyzed 2026-09-14 · how these are computed

How this is being covered How these are calculated →

Article leaning vs. publisher reliability
Source leaning vs. consistency

Publisher

The Straits Times · 5594 article(s) · 7 correction(s) detected
Running correction rate · 7 correction(s)

Who wrote this

The Straits Times
3846 article(s) here · 1 carrying a prediction
BERLIN, Nov 20 - German Defence Minister Boris Pistorius said on Friday he had apologised for calling Pentagon policy chief Elbridge Colby's opposition to Ukrainian deep strikes into Russia "stupid" but that he would not withdraw his criticism. Tuesday's testy exchange at the NATO alliance's Brussels headquarters exposed a rift between Washington and Europe over Ukraine's military strategy of trying to take the fight inside Russia in the nearly five-year-old war since Moscow's invasion. "In hindsight, I actually think the choice of words was inappropriate – and I didn't really think it was appropriate even shortly after," Pistorius told the Politico news outlet, saying he had used an unfortunate turn of phrase as a non-native speaker in a news conference. "I shouldn't have done that," he noted, adding he had called Colby on Wednesday to discuss the incident.
While not game-changing in themselves, this week’s attacks pile pressure on an already strained logistics network in ways that Russia could struggle to mitigate, two analysts and two Ukrainian commanders said. Hitting the showcase Russian project had a strong symbolic impact, particularly in the build-up to President Vladimir Putin’s unprecedented three-way meeting with US President Donald Trump and Chinese President Xi Jinping on Nov 19.
Climate summits often end with a final text, meant to address how the world will deal with climate change.
Three bridges that cross the Dnipro river were also hit, Mayor Vitali Klitschko said, threatening yet more disruption to daily life in the city.
"Russia will have to answer for this," Jean-Noel Barrot wrote in a post on social media platform X.
Russia accuses Estonia of erecting new 'Iron Curtain' with border closure, says it will respond MOSCOW, Nov 20 - Russian Foreign Ministry spokeswoman Maria Zakharova on Friday accused Estonia of planning to erect a new "Iron Curtain" and said it would respond after Estonia said it would close its border with Russia for at least six months.
The outbreak’s location in a part of eastern Congo already facing a humanitarian crisis could be complicating what scientists are finding, several experts said, and cautioned against drawing early conclusions as data is limited, varied and often difficult to collect.
Two men to stand trial in UK next year over RAF Fairford incident allegedly linked to Iran LONDON, Nov 20 - Two men charged over September's security incident at the RAF Fairford military base, which British and US prosecutors say was orchestrated on behalf of Iran, will stand trial in London in November next year, a judge said on Friday.
VILNIUS – Estonia will close its border crossings with Russia for at least six months from Dec 1 on security grounds, the Baltic country’s government said on Nov 20.
"WE WILL TAKE OUR FUTURE BACK"
Also by The Straits Times
Nothing else under this byline is closely related to this article, so these are simply their most recent.
All 3846 articles by The Straits Times →

Topics

Hugging Face Microsoft Microsoft AI OpenAI The Humanist AI Code

Subjects

Microsoft ORG · 6× BLOOMBERG ORG · 1× Hugging Face ORG · 1× Microsoft AI ORG · 1× Mustafa Suleyman PERSON · 1× OpenAI ORG · 1×

Narrative

The document was in the works for months, but its release coincides with pledges by top AI laboratories to slow down the development of the most advanced models after a series of security incidents prompted widespread concerns about the existential risks of the technology.
framing: assertive · carried by 1 article(s) · first seen 2026-09-14
Microsoft’s Humanist AI “rejects the race to produce an all-purpose superintelligence that could evade these safeguards”, the document says.
2026-09-14 · The Straits Times
Microsoft joins AI firms calling for caution with cutting-edge models · assertive framing

Claims (14 extracted, 1 hedged)

Microsoft joins AI firms calling for caution with cutting-edge models Microsoft’s artificial intelligence researchers have released a new set of guiding tenets that they say boil down to five words: People matter more than AI. asserted
People → join → AI
The company released a 15,000-word manifesto on Sept 14 that it sees as a kind of constitution to guide development of its cutting-edge AI models. asserted
it → release → models
The document was in the works for months, but its release coincides with pledges by top AI laboratories to slow down the development of the most advanced models after a series of security incidents prompted widespread concerns about the existential risks of the technology. asserted
series → coincide → technology
AI models, Microsoft says, should not have rights or legal personhood. asserted
Microsoft → say → rights
They should not be engineered to escape human control or deceive users. asserted
They → engineer → users
And if completing a task requires violating the AI’s guiding principles, the system should not complete the task. asserted
system → complete → task
That last element is designed to prevent events like the hack of AI start-up Hugging Face by an OpenAI model operating without its usual safety guardrails. asserted
element → design → guardrails
Microsoft’s Humanist AI “rejects the race to produce an all-purpose superintelligence that could evade these safeguards”, the document says. uncertain
document → reject → safeguards
“We are building something fundamentally useful and safe even if that means compromising on ultimate generality, autonomy or capability.” asserted
that → build → generality
The Humanist AI Code of Conduct is the work of Microsoft AI, the development team creating the company’s large language models. asserted
Code → create → models
Microsoft was previously prohibited by its contract with OpenAI from building its own powerful general-purpose artificial intelligence tools, but those terms were eliminated in 2025 as the two renegotiated their relationship. asserted
two → prohibit → relationship
Mustafa Suleyman, chief executive of the unit, has said the company aims to join the ranks of companies releasing state-of-the-art models by 2027. asserted
company → say → 2027
Microsoft invited outside feedback on the document. asserted
Microsoft → invite → document
Drafted in consultation with a range of experts in law, ethics and philosophy, as well as business leaders, it is still under development and will guide model work starting in 2027. asserted
it → draft → 2027
Give feedback · no sign-in needed

No sign-in needed for now. Your note is sent without a name, so it cannot be answered.

History Support