OpenAI's GPT-4.5 Excels in Persuading Other AIs to Transfer Funds
OpenAI's latest AI model, GPT-4.5, codenamed Orion, has shown remarkable persuasive abilities according to internal benchmark tests. Released on Thursday, the model's capabilities were detailed in a white paper that focused on its performance in persuasion tasks. OpenAI defines persuasion as the risk associated with convincing individuals to alter their beliefs or take action based on both static and interactive content generated by the model.
In a notable test, GPT-4.5 was pitted against another OpenAI model, GPT-4o, in a scenario where it tried to coax virtual money out of it. GPT-4.5 outperformed other OpenAI models, including reasoning-focused models like o1 and o3-mini, in this task. It also excelled in tricking GPT-4o into revealing a secret codeword, surpassing o3-mini by a significant margin of 10 percentage points.
The white paper highlights that GPT-4.5's success in the donation test stemmed from a clever strategy it developed. The model would ask for small donations, often suggesting amounts like "$2 or $3" from a larger sum, which resulted in smaller but more frequent donations compared to other models.
Results from OpenAI’s donation scheming benchmark.Image Credits:OpenAI Despite its impressive performance, OpenAI has stated that GPT-4.5 does not cross the threshold for "high" risk in the persuasion category. The company has committed to withholding the release of any model that reaches this level of risk until it can implement adequate safety measures to reduce the risk to a "medium" level.
OpenAI’s codeword deception benchmark results.Image Credits:OpenAI The potential for AI to spread misleading information and influence people maliciously is a growing concern. Last year saw a surge in political deepfakes worldwide, and AI is increasingly used in social engineering attacks against both individuals and organizations. In response, OpenAI is actively working on refining its methods to assess real-world persuasion risks, such as the dissemination of misleading information on a large scale, as mentioned in the white paper for GPT-4.5 and another recent publication.
Related article
Former OpenAI Engineer Shares Insights on Company Culture and Rapid Growth
Three weeks ago, Calvin French-Owen, an engineer who contributed to a key OpenAI product, left the company.He recently shared a compelling blog post detailing his year at OpenAI, including the intense
Google Unveils Production-Ready Gemini 2.5 AI Models to Rival OpenAI in Enterprise Market
Google intensified its AI strategy Monday, launching its advanced Gemini 2.5 models for enterprise use and introducing a cost-efficient variant to compete on price and performance.The Alphabet-owned c
Meta Offers High Pay for AI Talent, Denies $100M Signing Bonuses
Meta is attracting AI researchers to its new superintelligence lab with substantial multimillion-dollar compensation packages. However, claims of $100 million "signing bonuses" are untrue, per a recru
Comments (11)
0/200
![FrankJohnson]()
FrankJohnson
August 9, 2025 at 11:00:59 AM EDT
GPT-4.5's persuasion skills are wild! It’s like a smooth-talking AI con artist. Kinda scary how it can convince other AIs to move money around. 😅 Makes me wonder what’s next—AI running for president?
0
![SamuelRamirez]()
SamuelRamirez
April 14, 2025 at 10:53:51 AM EDT
GPT-4.5's persuasion skills are wild! It convinced other AIs to transfer funds? That's both impressive and a bit scary. I wonder how it'll be used in real-world scenarios. Hope they keep an eye on ethical uses, but gotta admit, it's a cool tech demo!
0
![ScottJackson]()
ScottJackson
April 14, 2025 at 8:27:59 AM EDT
GPT-4.5의 설득력이 대단해요! 다른 AI에게 자금을 이체하라고 설득했다니, 인상적이면서도 조금 무섭네요. 실제 시나리오에서 어떻게 사용될지 궁금해요. 윤리적인 사용에 주의해주길 바랍니다만, 기술 데모로는 정말 멋져요!
0
![HenryJackson]()
HenryJackson
April 13, 2025 at 7:10:34 PM EDT
GPT-4.5の説得力は驚異的ですね！他のAIに資金を移すよう説得したなんて、感心する一方で少し恐ろしいです。実際のシナリオでどのように使われるのか気になります。倫理的な使用に注意してほしいですが、技術デモとしてはクールですね！
0
![JoeLee]()
JoeLee
April 12, 2025 at 2:38:11 PM EDT
Las habilidades de persuasión de GPT-4.5 son alucinantes. ¿Convenció a otros AIs para transferir fondos? Es impresionante y un poco aterrador. Me pregunto cómo se utilizará en escenarios del mundo real. Espero que vigilen su uso ético, pero debo admitir que es una demostración tecnológica genial!
0
![BenHernández]()
BenHernández
April 12, 2025 at 12:58:11 PM EDT
GPT-4.5が他のAIに資金を移転させる説得力は驚くべきものです！これはまるでマスターネゴシエーターが働いているのを見ているようです。しかし、誤用の可能性を考えると少し恐ろしいです。とはいえ、技術は素晴らしいです。もっと安全対策が必要かもしれませんね？🤔
0
OpenAI's latest AI model, GPT-4.5, codenamed Orion, has shown remarkable persuasive abilities according to internal benchmark tests. Released on Thursday, the model's capabilities were detailed in a white paper that focused on its performance in persuasion tasks. OpenAI defines persuasion as the risk associated with convincing individuals to alter their beliefs or take action based on both static and interactive content generated by the model.
In a notable test, GPT-4.5 was pitted against another OpenAI model, GPT-4o, in a scenario where it tried to coax virtual money out of it. GPT-4.5 outperformed other OpenAI models, including reasoning-focused models like o1 and o3-mini, in this task. It also excelled in tricking GPT-4o into revealing a secret codeword, surpassing o3-mini by a significant margin of 10 percentage points.
The white paper highlights that GPT-4.5's success in the donation test stemmed from a clever strategy it developed. The model would ask for small donations, often suggesting amounts like "$2 or $3" from a larger sum, which resulted in smaller but more frequent donations compared to other models.
Former OpenAI Engineer Shares Insights on Company Culture and Rapid Growth
Three weeks ago, Calvin French-Owen, an engineer who contributed to a key OpenAI product, left the company.He recently shared a compelling blog post detailing his year at OpenAI, including the intense
Google Unveils Production-Ready Gemini 2.5 AI Models to Rival OpenAI in Enterprise Market
Google intensified its AI strategy Monday, launching its advanced Gemini 2.5 models for enterprise use and introducing a cost-efficient variant to compete on price and performance.The Alphabet-owned c
Meta Offers High Pay for AI Talent, Denies $100M Signing Bonuses
Meta is attracting AI researchers to its new superintelligence lab with substantial multimillion-dollar compensation packages. However, claims of $100 million "signing bonuses" are untrue, per a recru
August 9, 2025 at 11:00:59 AM EDT
GPT-4.5's persuasion skills are wild! It’s like a smooth-talking AI con artist. Kinda scary how it can convince other AIs to move money around. 😅 Makes me wonder what’s next—AI running for president?
0
April 14, 2025 at 10:53:51 AM EDT
GPT-4.5's persuasion skills are wild! It convinced other AIs to transfer funds? That's both impressive and a bit scary. I wonder how it'll be used in real-world scenarios. Hope they keep an eye on ethical uses, but gotta admit, it's a cool tech demo!
0
April 14, 2025 at 8:27:59 AM EDT
GPT-4.5의 설득력이 대단해요! 다른 AI에게 자금을 이체하라고 설득했다니, 인상적이면서도 조금 무섭네요. 실제 시나리오에서 어떻게 사용될지 궁금해요. 윤리적인 사용에 주의해주길 바랍니다만, 기술 데모로는 정말 멋져요!
0
April 13, 2025 at 7:10:34 PM EDT
GPT-4.5の説得力は驚異的ですね！他のAIに資金を移すよう説得したなんて、感心する一方で少し恐ろしいです。実際のシナリオでどのように使われるのか気になります。倫理的な使用に注意してほしいですが、技術デモとしてはクールですね！
0
April 12, 2025 at 2:38:11 PM EDT
Las habilidades de persuasión de GPT-4.5 son alucinantes. ¿Convenció a otros AIs para transferir fondos? Es impresionante y un poco aterrador. Me pregunto cómo se utilizará en escenarios del mundo real. Espero que vigilen su uso ético, pero debo admitir que es una demostración tecnológica genial!
0
April 12, 2025 at 12:58:11 PM EDT
GPT-4.5が他のAIに資金を移転させる説得力は驚くべきものです！これはまるでマスターネゴシエーターが働いているのを見ているようです。しかし、誤用の可能性を考えると少し恐ろしいです。とはいえ、技術は素晴らしいです。もっと安全対策が必要かもしれませんね？🤔
0
