Source A
OpenAI выпустила флагманскую модель GPT-5.4: самый мощный ИИ компании
hi-tech.mail.ru
https://hi-tech.mail.ru/news/143809-openai-vypustila-flagmanskuyu-model-gpt-54-samyj-moshnyj-ii-kompanii/
Comparison
Winner: Source A is less manipulative
Source A appears less manipulative than Source B for this narrative.
Source B
OpenAI says new GPT-5 models show major drop in political bias
foxnews.com
https://www.foxnews.com/media/openai-says-new-gpt-5-models-show-major-drop-political-bias
Topics
Instant verdict
Less biased source: Source A
More emotional framing: Source B
More one-sided framing: Tie
Weaker evidence quality: Tie
More manipulative overall: Source B
Narrative conflict
Source A main narrative
Нейросеть может пользоваться компьютером и поддерживает контекст до 1 млн токенов.
Source B main narrative
OpenAI says this is part of a commitment to "cooperative orientation" and shared standards for AI objectivity.
Conflict summary
Stance contrast: emphasis on economic factors versus emphasis on territorial control.
Source A stance
Нейросеть может пользоваться компьютером и поддерживает контекст до 1 млн токенов.
Stance confidence: 72%
Source B stance
OpenAI says this is part of a commitment to "cooperative orientation" and shared standards for AI objectivity.
Stance confidence: 77%
Central stance contrast
Stance contrast: emphasis on economic factors versus emphasis on territorial control.
Why this pair fits comparison
- Candidate type: Closest similar
- Comparison quality: 48%
- Event overlap score: 15%
- Contrast score: 79%
- Contrast strength: Weak but valid compare
- Stance contrast strength: High
- Event overlap: Event overlap is weak. Issue framing and action profile overlap.
- Contrast signal: Interpretive contrast is visible, but event linkage is moderate: verify against primary sources.
- Why conflict is limited: Some contrast exists, but event linkage is weak: this is closer to an adjacent angle than a strong battle pair.
- Stronger comparison suggestion: This direct pair is weak: open conflict-mode similar search to pick a stronger contrast angle.
- Use stronger suggestion
Key claims and evidence
Key claims in source A
- Нейросеть может пользоваться компьютером и поддерживает контекст до 1 млн токенов.
- Версия GPT-5.4 Thinking теперь может заранее показывать план рассуждений.
- Пользователь может изменить направление работы модели еще во время формирования ответа и получить результат, который лучше соответствует задаче без дополнительных запросов.
- это самая мощная и эффективная модель для профессиональной работы от создателей ChatGPT.
Key claims in source B
- OpenAI says this is part of a commitment to "cooperative orientation" and shared standards for AI objectivity.
- OpenAI’s new GPT-5 models reduced political bias by roughly 30% compared to GPT-4o.
- OpenAI says its latest generation of artificial intelligence (AI) models, including GPT-5 Instant and GPT-5 Thinking, show a significant reduction in political bias compared to previous versions, according to a new inte…
- OpenAI also analyzed real-world user data and found that less than 0.01% of ChatGPT responses showed any signs of political bias, an amount the company calls "rare and low severity.""GPT-5 Instant and GPT-5 Thinking sho…
Text evidence
Evidence from source A
-
key claim
Нейросеть может пользоваться компьютером и поддерживает контекст до 1 млн токенов.
A key claim that anchors the narrative framing.
-
key claim
Версия GPT-5.4 Thinking теперь может заранее показывать план рассуждений.
A key claim that anchors the narrative framing.
-
evaluative label
Сравнение GPT-5.4 с другими моделямиИсточник: OpenAIРазработчики также улучшили возможности глубокого поиска информации в интернете, в том числе при работе со сложными и узкоспециализирован…
Evaluative labeling that nudges a normative interpretation.
-
selective emphasis
Кроме того, в начале марта OpenAI выпустила GPT-5.3 Instant — улучшенную модель для повседневного общения.
Possible selective emphasis on specific aspects of the story.
-
omission candidate
According to the data, OpenAI’s new GPT-5 models reduced political bias by roughly 30% compared to GPT-4o.
Possible context omission: Source A gives less emphasis to territorial control dimension than Source B.
Evidence from source B
-
key claim
According to the data, OpenAI’s new GPT-5 models reduced political bias by roughly 30% compared to GPT-4o.
A key claim that anchors the narrative framing.
-
key claim
OpenAI also analyzed real-world user data and found that less than 0.01% of ChatGPT responses showed any signs of political bias, an amount the company calls "rare and low severity.""GPT-5…
A key claim that anchors the narrative framing.
-
selective emphasis
That only works if they trust ChatGPT to be objective." CHATGPT WILL NOW COMBAT BIAS WITH NEW MEASURES PUT FORTH BY OPENAI In this photo illustration, a smartphone screen shows Sora by Open…
Possible selective emphasis on specific aspects of the story.
Bias/manipulation evidence
-
Source A · Framing effect
Кроме того, в начале марта OpenAI выпустила GPT-5.3 Instant — улучшенную модель для повседневного общения.
Possible framing pattern: wording sets a specific interpretation frame rather than neutral description.
-
Source B · Framing effect
That only works if they trust ChatGPT to be objective." CHATGPT WILL NOW COMBAT BIAS WITH NEW MEASURES PUT FORTH BY OPENAI In this photo illustration, a smartphone screen shows Sora by Open…
Possible framing pattern: wording sets a specific interpretation frame rather than neutral description.
How score signals are formed
Bias score signal
Bias signal combines framing pressure, emotional wording, selective emphasis, and one-sided narrative markers.
Emotionality signal
Emotionality rises when evidence contains emotionally loaded wording and evaluative labels.
One-sidedness signal
One-sidedness rises when one frame dominates and alternative interpretations are weakly represented.
Evidence strength signal
Evidence strength rises with concrete claims, attributed statements, and verifiable contextual support.
Source A
26%
emotionality: 25 · one-sidedness: 30
Detected in Source A
framing effect
Source B
42%
emotionality: 74 · one-sidedness: 30
Detected in Source B
framing effect
Metrics
Framing differences
- Source A emotionality: 25/100 vs Source B: 74/100
- Source A one-sidedness: 30/100 vs Source B: 30/100
- Stance contrast: emphasis on economic factors versus emphasis on territorial control.
Possible omitted/downplayed context
- Source A appears to downplay context related to territorial control dimension.