Close Menu
  • Home
  • AI Models
    • DeepSeek
    • xAI
    • OpenAI
    • Meta AI Llama
    • Google DeepMind
    • Amazon AWS AI
    • Microsoft AI
    • Anthropic (Claude)
    • NVIDIA AI
    • IBM WatsonX Granite 3.1
    • Adobe Sensi
    • Hugging Face
    • Alibaba Cloud (Qwen)
    • Baidu (ERNIE)
    • C3 AI
    • DataRobot
    • Mistral AI
    • Moonshot AI (Kimi)
    • Google Gemma
    • xAI
    • Stability AI
    • H20.ai
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Microsoft Research
    • Meta AI Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding & Startups
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • Expert Insights & Videos
    • Google DeepMind
    • Lex Fridman
    • Matt Wolfe AI
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • Matt Wolfe AI
    • The TechLead
    • Andrew Ng
    • OpenAI
  • Expert Blogs
    • François Chollet
    • Gary Marcus
    • IBM
    • Jack Clark
    • Jeremy Howard
    • Melanie Mitchell
    • Andrew Ng
    • Andrej Karpathy
    • Sebastian Ruder
    • Rachel Thomas
    • IBM
  • AI Policy & Ethics
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
    • EFF AI
    • European Commission AI
    • Partnership on AI
    • Stanford HAI Policy
    • Mozilla Foundation AI
    • Future of Life Institute
    • Center for AI Safety
    • World Economic Forum AI
  • AI Tools & Product Releases
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
    • Image Generation
    • Video Generation
    • Writing Tools
    • AI for Recruitment
    • Voice/Audio Generation
  • Industry Applications
    • Finance AI
    • Healthcare AI
    • Legal AI
    • Manufacturing AI
    • Media & Entertainment
    • Transportation AI
    • Education AI
    • Retail AI
    • Agriculture AI
    • Energy AI
  • AI Art & Entertainment
    • AI Art News Blog
    • Artvy Blog » AI Art Blog
    • Weird Wonderful AI Art Blog
    • The Chainsaw » AI Art
    • Artvy Blog » AI Art Blog
What's Hot

Tencent’s Hunyuan Team Releases Open-Source Hunyuan3D World Model 1.0, Can Generate Explorable 3D Worlds

Icertis Partners With Dioptra – 3rd AI Deal in 18 Months – Artificial Lawyer

The DeepSeek moment: China’s economic threat

Facebook X (Twitter) Instagram
Advanced AI News
  • Home
  • AI Models
    • OpenAI (GPT-4 / GPT-4o)
    • Anthropic (Claude 3)
    • Google DeepMind (Gemini)
    • Meta (LLaMA)
    • Cohere (Command R)
    • Amazon (Titan)
    • IBM (Watsonx)
    • Inflection AI (Pi)
  • AI Research
    • Allen Institue for AI
    • arXiv AI
    • Berkeley AI Research
    • CMU AI
    • Google Research
    • Meta AI Research
    • Microsoft Research
    • OpenAI Research
    • Stanford HAI
    • MIT CSAIL
    • Harvard AI
  • AI Funding
    • AI Funding Database
    • CBInsights AI
    • Crunchbase AI
    • Data Robot Blog
    • TechCrunch AI
    • VentureBeat AI
    • The Information AI
    • Sifted AI
    • WIRED AI
    • Fortune AI
    • PitchBook
    • TechRepublic
    • SiliconANGLE – Big Data
    • MIT News
    • Data Robot Blog
  • AI Experts
    • Google DeepMind
    • Lex Fridman
    • Meta AI Llama
    • Yannic Kilcher
    • Two Minute Papers
    • AI Explained
    • TheAIEdge
    • The TechLead
    • Matt Wolfe AI
    • Andrew Ng
    • OpenAI
    • Expert Blogs
      • François Chollet
      • Gary Marcus
      • IBM
      • Jack Clark
      • Jeremy Howard
      • Melanie Mitchell
      • Andrew Ng
      • Andrej Karpathy
      • Sebastian Ruder
      • Rachel Thomas
      • IBM
  • AI Tools
    • AI Assistants
    • AI for Recruitment
    • AI Search
    • Coding Assistants
    • Customer Service AI
  • AI Policy
    • ACLU AI
    • AI Now Institute
    • Center for AI Safety
  • Industry AI
    • Finance AI
    • Healthcare AI
    • Education AI
    • Energy AI
    • Legal AI
LinkedIn Instagram YouTube Threads X (Twitter)
Advanced AI News
Industry Applications

ChatGPT Has No Legal Privilege – Is This A Problem? – Artificial Lawyer

By Advanced AI EditorJuly 28, 2025No Comments5 Mins Read
Share Facebook Twitter Pinterest Copy Link Telegram LinkedIn Tumblr Email
Share
Facebook Twitter LinkedIn Pinterest Email



Last week, OpenAI’s CEO Sam Altman said in a podcast that ChatGPT does not provide legal privilege or ‘legal confidentiality’ and ‘we haven’t figured that out yet’. Understandably that’s freaked out some lawyers, both in terms of privacy and also the potential for exposure to subpoenas for information that is shared with the LLM. How big a problem is this?

First, let’s look at what he said.  

In the transcript (via Tech Crunch – see link) Altman said: ‘People talk about the most personal [stuff] in their lives to ChatGPT. People use it – young people, especially, use it – as a therapist, a life coach; having these relationship problems and [asking] ‘what should I do?’

‘And right now, if you talk to a therapist or a lawyer or a doctor about those problems, there’s legal privilege for it. There’s doctor-patient confidentiality, there’s legal confidentiality, whatever. And we haven’t figured that out yet for when you talk to ChatGPT.’

‘I think that’s very screwed up. I think we should have the same concept of privacy for your conversations with AI that we do with a therapist or whatever – and no one had to think about that even a year ago.’

–

Is This a Problem?

Well, who better to ask than ChatGPT itself. First the subpoena issue.

This is what it told AL (Note: the following are unedited, verbatim responses from ChatGPT – and naturally this should not be seen as legal advice 🙂 )

‘Yes, information shared with ChatGPT can potentially be subpoenaed, but only under very specific circumstances. Here’s a breakdown of what that means in practice:

1. What OpenAI Says About Data Use

OpenAI, the company behind ChatGPT, has a strong privacy policy. According to its privacy policy, OpenAI does not store or use your conversations to train its models if you’re using ChatGPT with a paid subscription and chat history disabled.

2. Legal Subpoenas

A subpoena is a legal document that compels an individual or organization to provide evidence or testify. In theory:

If OpenAI stores your data, it could be compelled to hand it over under a subpoena or court order.

If data is not stored, there is nothing to subpoena.

ChatGPT chats (especially with chat history off) are not publicly available, and OpenAI does not sell your data.But stored conversations (with history on) could be legally accessible in very rare and serious cases (e.g., criminal investigations).

 3. Best Practices for Confidentiality

If you’re sharing sensitive, personal, or legally privileged information:

Turn off chat history before starting the conversation.

Do not treat ChatGPT like a lawyer, doctor, or therapist—it does not have legal privilege or confidentiality protections like those professions do.

If you’re handling regulated or confidential data (e.g. client legal info), do not input it into ChatGPT without safeguards.

 TL;DR:

Can a court subpoena ChatGPT data? Technically yes, but only if it exists and is relevant.

Does OpenAI store your chats? Not if chat history is off or you’re using certain paid plans with data controls.

Should you put confidential legal info in ChatGPT? No, unless you’re confident in the data protection settings and are not risking client confidentiality.

—

So, it’s saying that basically: yes, it could be a risk, but only if the data is actually still there, which it may well not be.

—

And one more question: is the lack of legal privilege also a wider risk for lawyers using ChatGPT? Here’s what it told AL. (Note: the following are unedited, verbatim responses from ChatGPT – and naturally this should not be seen as legal advice 🙂 )

‘Great question – the short answer is: no, you should not put truly confidential or sensitive information into ChatGPT, unless you’re using a version of the service designed specifically for that level of data privacy (e.g. OpenAI’s enterprise-grade offerings).

Here’s the breakdown:

Standard ChatGPT (Free or Plus)

Not secure for confidential legal, personal, or client data.

Your data is not used to train the model (if chat history & training is off), but it can still be stored temporarily and reviewed in rare cases for abuse monitoring or quality assurance.

No encryption at rest specifically designed for sensitive data.

No legal privilege or compliance with data protection regulations like GDPR/CCPA for sensitive information.

So: Do not share names, addresses, contracts, or client details in the normal consumer version of ChatGPT.

ChatGPT Enterprise or API (Business Use)

If you’re building a legal tech product or using ChatGPT in a professional legal environment, OpenAI offers:

Enterprise ChatGPT or API access

No data ever stored or used for training

Data encryption in transit and at rest

SOC 2 compliance and better audit controls

Can be integrated into your own secure environment

This setup can be safe for confidential information — if your overall system is secure and compliant.’

—

So, as we’ve explored before, using a ‘raw’ LLM is a bad idea, even if OpenAI will most likely never bother to look at your specific inputs. But, if you are using an enterprise approach then you are on safer ground, it would appear. But…always check with someone who knows…!

As to the subpoena point, even ChatGPT says that it’s possible, but that circumstances where that actually happened would be rare. Or so it claims.

Of course – these points are made by the LLM in question and thus should be A) not seen as legal advice, and B) taken with a pinch of salt given that this is the ‘accused’ defending itself.

–

What do you think?

—

( Main pic: Sam Altman, via Wikipedia Creative Commons – CC credit: By TechCrunch – TechCrunch Disrupt San Francisco 2019 – Day 2, CC BY 2.0. )

Discover more from Artificial Lawyer

Subscribe to get the latest posts sent to your email.



Source link

Follow on Google News Follow on Flipboard
Share. Facebook Twitter Pinterest LinkedIn Tumblr Email Copy Link
Previous ArticleRunway Unveils Aleph Video-to-Video AI Model That Can Be Used for Post-Production
Next Article Mistral AI & Qualcomm partner will boost AI on Snapdragon devices
Advanced AI Editor
  • Website

Related Posts

Icertis Partners With Dioptra – 3rd AI Deal in 18 Months – Artificial Lawyer

July 28, 2025

Will Lovable Change Legal Tech Development Forever? – Artificial Lawyer

July 28, 2025

Tesla’s new affordable Model Y details teased in new sighting

July 28, 2025

Comments are closed.

Latest Posts

Scottish Museum Group Warns of ‘Policing of Gender’—and More Art News

David Geffen Sued By Estranged Husband for Breach of Contract

Auction House Will Sell Egyptian Artifact Despite Concern From Experts

Anish Kapoor Lists New York Apartment for $17.75 M.

Latest Posts

Tencent’s Hunyuan Team Releases Open-Source Hunyuan3D World Model 1.0, Can Generate Explorable 3D Worlds

July 28, 2025

Icertis Partners With Dioptra – 3rd AI Deal in 18 Months – Artificial Lawyer

July 28, 2025

The DeepSeek moment: China’s economic threat

July 28, 2025

Subscribe to News

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

Recent Posts

  • Tencent’s Hunyuan Team Releases Open-Source Hunyuan3D World Model 1.0, Can Generate Explorable 3D Worlds
  • Icertis Partners With Dioptra – 3rd AI Deal in 18 Months – Artificial Lawyer
  • The DeepSeek moment: China’s economic threat
  • Alibaba Stock Climbs on AI?Powered Smart Glasses Debut
  • Huawei Challenges Nvidia with New AI Compute Platform

Recent Comments

  1. binance推薦獎金 on [2407.11104] Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conception
  2. психолог онлайн индивидуально on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  3. GeraldDes on 1-800-CHAT-GPT—12 Days of OpenAI: Day 10
  4. binance sign up on Inclusion Strategies in Workplace | Recruiting News Network
  5. Rejestracja on Online Education – How I Make My Videos

Welcome to Advanced AI News—your ultimate destination for the latest advancements, insights, and breakthroughs in artificial intelligence.

At Advanced AI News, we are passionate about keeping you informed on the cutting edge of AI technology, from groundbreaking research to emerging startups, expert insights, and real-world applications. Our mission is to deliver high-quality, up-to-date, and insightful content that empowers AI enthusiasts, professionals, and businesses to stay ahead in this fast-evolving field.

Subscribe to Updates

Subscribe to our newsletter and never miss our latest news

Subscribe my Newsletter for New Posts & tips Let's stay updated!

LinkedIn Instagram YouTube Threads X (Twitter)
  • Home
  • About Us
  • Advertise With Us
  • Contact Us
  • DMCA
  • Privacy Policy
  • Terms & Conditions
© 2025 advancedainews. Designed by advancedainews.

Type above and press Enter to search. Press Esc to cancel.