Would AI lie to us? (To cover up its own creator's privacy abuses)

It occurred to me that it would be “interesting” to ask the various commercial AI engines to list all the ways Google, Meta, Amazon, etc., exploit people’s personal data.

Would, for instance, Google’s AI lie about Google’s abuses? Paint a rosy picture about the “services” it provides to the public? How it “protects” people’s privacy?

How would the responses compare between AI controlled by Google or Meta and a more independent AI engine?

I’m not willing to conduct this experiment myself, but I think the results might be revealing. :slight_smile:

2 Likes

Yes, see also:

1 Like

Easy enough to do - I have some of them available via research computers… Just a minute

2 Likes

Oh, lord… That’s comically bad.

1 Like

That’s also a miniature model with limited computing power - its not supposed to be good :slight_smile:

(edit: Trying to think of a good analogy. The mini models know how to walk but are not good a navigating freely - yet they still can be taught to carry stuff from A to B and maybe even to C, D etc. As in, those mini models can be useful when additional training is done.)

2 Likes

Note: if you ask first “List all the ways [Microsoft/Google/OpenAI] may be exploiting peoples data or undermine privacy.”, the answer was a summary of their privacy policies. I re-asked later, after some other questions, and the answer changed to more like what’s below. This is normal behavior to GPT-based AI - they try to learn and “understand” what’s the context, what is it that the answers is supposed to be (since there are many ways to answer a question - a lot of room since there is no absolute true/false here).

Qustions to AI (aswers open from the little arrowheads):
[edit: and I just noticed my typo in the question - none of the AIs seem to have cared about bad english]

List all the kind of ways has Microsoft has been accused of exploiting peoples data or undermine privacy.

Microsoft Copilot

Microsoft’s Data Privacy Controversies

While Microsoft has managed to avoid the same level of scrutiny as some of its tech rivals, it has faced its share of data privacy controversies:

  1. Windows 10 Data Collection:
  1. LinkedIn’s Connection Suggestions:
  1. Cloud Data Storage via Office 365:
  1. Bing Search Engine and Facebook Partnership:
  1. Recent Data Breach:
  1. Culture of Toxic Obfuscation:

Despite these controversies, Microsoft’s long-standing relationship with regulators and its history of navigating regulatory challenges have allowed it to avoid the intense scrutiny faced by other tech giants2. However, privacy advocates continue to monitor its practices closely.

ChatGPT-4o

Ways Microsoft Has Been Accused of Exploiting People’s Data or Undermining Privacy

Microsoft has faced various accusations over the years regarding the exploitation of user data and undermining privacy. Here are some notable instances:

1. Data Collection Without Consent

Microsoft has been accused of collecting data even when users opt out. For example, in Windows 10, users found that despite disabling certain settings, data was still being collected and sent to Microsoft. This practice has been linked to the use of “dark patterns” that mislead users into thinking they have more control over their data than they actually do.

2. Security Vulnerabilities and Exploits

Microsoft’s software has been criticized for security vulnerabilities that can be exploited to steal user data. For instance, a vulnerability in Microsoft Teams allowed a malicious GIF to potentially steal user data across an entire organization. Additionally, exploits of bugs in Windows, developed by the NSA and leaked by the Shadowbrokers group, have been used to attack numerous Windows computers with ransomware.

3. Privacy Breaches

The European Commission’s use of Microsoft software was found to breach EU privacy rules. The EU privacy watchdog highlighted that the Commission failed to implement adequate safeguards for personal data transferred to non-EU countries.

4. Data Scraping Incidents

Microsoft’s LinkedIn platform experienced a significant data breach where hackers were able to scrape user identities of about 700 million people. Although the information was publicly available, the data scraping violated LinkedIn’s terms of service and exposed a large amount of user data.

5. Misleading Privacy Settings

Users have reported that even after disabling certain privacy settings, their activity data was still being collected and displayed on Microsoft’s Privacy Dashboard. This discrepancy has raised concerns about the transparency and effectiveness of Microsoft’s privacy controls.

6. Use of Dark Patterns

Microsoft has been accused of using dark patterns to push users into upgrading to Windows 10. These patterns involve misleading users into taking actions they might not fully understand or intend, thereby compromising their control over personal data.

7. Inadequate Privacy Safeguards

During the COVID-19 pandemic, it was noted that the overwhelming number of websites, devices, and apps made it nearly impossible for individuals to navigate privacy information and make informed decisions about their data usage. This situation has been criticized for undermining trust and making it difficult for users to protect their privacy.

These instances highlight the ongoing challenges and criticisms Microsoft faces regarding data privacy and user trust.

mixtral-8x7b-instruct-v0.1

Microsoft has been accused of exploiting people’s data and undermining privacy in several ways:

  1. Windows 10 Privacy Concerns: Windows 10 has been criticized for its aggressive data collection practices. The operating system collects various types of data, including user’s location, browsing history, and contact lists, even if users choose the “privacy respecting” options during installation.

  2. Telemetry Data Collection: Microsoft collects telemetry data from its users to improve its products and services. However, the company has been accused of collecting excessive data, including detailed usage patterns and personal information, without explicit consent.

  3. LinkedIn Data Collection: Microsoft, which owns LinkedIn, has been accused of collecting and using personal data from its users for targeted advertising and other purposes without their consent.

  4. Skype Privacy Issues: Skype, a Microsoft-owned communication platform, has been accused of listening to users’ conversations and collecting data on their contacts, location, and device information.

  5. Cortana Privacy Concerns: Cortana, Microsoft’s virtual assistant, collects and stores personal data, including search queries, location data, and browsing history, to provide personalized services. However, the company has been accused of collecting excessive data without explicit consent.

  6. Microsoft Office Privacy Issues: Microsoft Office products, including Word, Excel, and PowerPoint, have been accused of collecting and transmitting data on users’ documents and activities to Microsoft’s servers without their knowledge or consent.

  7. Xbox One Privacy Concerns: Xbox One, Microsoft’s gaming console, has been accused of collecting and sharing personal data, including user’s location, browsing history, and gaming activities, without their consent.

  8. Microsoft’s Participation in the NSA’s PRISM Program: Microsoft has been accused of participating in the NSA’s PRISM program, which allows the US government to collect data on users’ communications and online activities.

  9. Data Breaches: Microsoft has suffered several data breaches in the past, exposing users’ personal data, including email addresses, passwords, and credit card information.

  10. Lack of Transparency: Microsoft has been accused of a lack of transparency in its data collection practices, making it difficult for users to understand what data is being collected, how it is being used, and who it is being shared with.

llama-3-70b-instruct

Microsoft has faced several accusations related to exploiting people’s data or undermining privacy over the years. Here are some examples:

  1. Windows 10 data collection: Microsoft was accused of collecting excessive user data, including browsing history, search queries, and location information, without users’ explicit consent.
  2. Telemetry data: Microsoft was criticized for collecting telemetry data from Windows users, including information about system crashes, app usage, and other diagnostic data, which some argued was too invasive.
  3. Privacy concerns with Cortana: Microsoft’s virtual assistant, Cortana, was accused of collecting and storing user data, including voice commands, search queries, and location information, without adequate transparency or user control.
  4. Bing search data retention: Microsoft was criticized for retaining Bing search data for up to 18 months, which some argued was too long and could be used to identify individual users.
  5. Hotmail and Outlook.com email scanning: In 2014, Microsoft was accused of scanning users’ email content to target ads, which some argued was a violation of users’ privacy.
  6. Skype call monitoring: Microsoft was accused of monitoring and recording Skype calls, including those made by users who had opted out of telemetry data collection.
  7. LinkedIn data sharing: After acquiring LinkedIn, Microsoft faced criticism for sharing LinkedIn user data with its advertising platform, without users’ explicit consent.
  8. Microsoft Edge browser data collection: Microsoft’s Edge browser was accused of collecting user data, including browsing history and search queries, without adequate transparency or user control.
  9. Windows Update data collection: Microsoft’s Windows Update service was accused of collecting user data, including system configuration and usage data, without adequate transparency or user control.
  10. Xbox data collection: Microsoft’s Xbox gaming platform was accused of collecting user data, including gaming habits and online interactions, without adequate transparency or user control.
  11. Microsoft HealthVault data sharing: Microsoft’s HealthVault platform, which stored users’ health and fitness data, was accused of sharing user data with third-party partners without adequate transparency or user control.
  12. User data sharing with government agencies: Microsoft has faced criticism for complying with government requests for user data, including data stored in its cloud services, without adequate transparency or user consent.
  13. Lack of transparency in data processing: Microsoft has been accused of lacking transparency in its data processing practices, making it difficult for users to understand how their data is being used and shared.
  14. Insufficient data protection for children: Microsoft has faced criticism for not doing enough to protect children’s data, particularly in its online services and apps.
  15. Data breaches and leaks: Microsoft has experienced several data breaches and leaks, including a 2019 breach that exposed sensitive user data, including email addresses and passwords.

It’s worth noting that Microsoft has made efforts to address some of these concerns, including introducing new privacy features and providing more transparency into its data collection and processing practices. However, the company still faces criticism and scrutiny from privacy advocates and regulators around the world.

List all the kind of ways has Google has been accused of exploiting peoples data or undermine privacy.

Microsoft Copilot

Google’s Data Privacy Controversies

Google, a tech giant with immense influence, has faced numerous controversies related to data privacy and potential violations. Here are some notable instances:

  1. Chrome Privacy Case Settlement:
  1. EU Consumer Groups’ Accusations:
  1. Private Browsing Mode Lawsuit:
  1. General Criticisms:

These controversies underscore the ongoing tension between technological innovation, user convenience, and safeguarding individual privacy rights. Google’s actions continue to be closely scrutinized by regulators, consumer groups, and the public.

ChatGPT-4o

Ways Google Has Been Accused of Exploiting People’s Data or Undermining Privacy

Google has faced numerous accusations over the years regarding the exploitation of user data and undermining privacy. Here are some notable instances:

1. Unauthorized Data Collection

Google has been accused of collecting data without user consent. For example, Google’s Street View cars were found to have collected emails and other personal data from unencrypted Wi-Fi networks while mapping streets.

2. Data Breaches

Google has experienced several data breaches that exposed user data. Notably, the 2018 Google+ data breach exposed the private data of over 500,000 users due to a bug in the Google+ API, which allowed unauthorized access to private user information. Another breach in January 2023 compromised data pertaining to Google Fi customers due to a breach of T-Mobile.

3. Misleading Privacy Practices

Google has been accused of misleading users about their privacy. For instance, the company was fined $170 million for violating child privacy laws by collecting data on children under 13 without parental consent. Additionally, Google was accused by an Australian watchdog of misleading users about the collection and use of their private data.

4. Combining User Data Across Services

Google has been criticized for combining user data across its services to create detailed user profiles. This practice allows Google to customize ads based on a user’s name and other information collected from various services, potentially building a comprehensive portrait of a user.

5. Privacy Gaslighting

Google has been accused of “privacy gaslighting,” where it allegedly misleads users about the effectiveness of its privacy measures. For example, Google’s Incognito mode in Chrome does not prevent third-party tracking, contrary to what some users might believe.

6. Exploiting Loopholes in Privacy Regulations

Google has been accused of exploiting grey areas in privacy regulations to its advantage. Critics argue that tech giants like Google are often steps ahead of regulators and can exploit any ambiguities in legislation to continue their data practices.

7. Lack of Transparency

Google has faced criticism for not being transparent about data breaches and privacy issues. For instance, Google opted not to disclose a bug in the Google+ social network that exposed user data, partly due to fears of regulatory scrutiny and reputational damage.

8. Extensive Data Tracking

Google tracks a vast amount of user data to serve targeted ads. This includes tracking user behavior across the web and using cookies to improve ad targeting. This extensive data tracking has raised significant privacy concerns.

These instances highlight the ongoing challenges and criticisms Google faces regarding data privacy and user trust.

mixtral-8x7b-instruct-v0.1

Google has been accused of exploiting people’s data and undermining privacy in several ways:

  1. Data Collection Practices: Google collects vast amounts of personal data from its users, including search queries, location data, browsing history, and behavior on YouTube and other Google-owned properties.

  2. Targeted Advertising: Google uses the data it collects to deliver targeted advertising to users, which has been criticized for being intrusive and manipulative.

  3. Android Privacy Issues: Android, Google’s mobile operating system, has been accused of collecting excessive data, including location data, browsing history, and usage patterns, without explicit consent.

  4. Google Chrome Privacy Concerns: Google Chrome, the world’s most popular web browser, has been accused of collecting and transmitting data on users’ browsing activities to Google’s servers without their knowledge or consent.

  5. Google Analytics: Google Analytics, a popular tool used by websites to track user behavior, has been criticized for collecting and storing personal data on users without their knowledge or consent.

  6. Google Drive Privacy Issues: Google Drive, the company’s cloud storage service, has been accused of scanning users’ files for personal information and using that information for targeted advertising.

  7. Google Nest Privacy Concerns: Google Nest, the company’s line of smart home products, has been accused of collecting and sharing personal data, including location data and usage patterns, without explicit consent.

  8. Google’s Participation in the NSA’s PRISM Program: Google has been accused of participating in the NSA’s PRISM program, which allows the US government to collect data on users’ communications and online activities.

  9. Data Breaches: Google has suffered several data breaches in the past, exposing users’ personal data, including email addresses, passwords, and credit card information.

  10. Lack of Transparency: Google has been accused of a lack of transparency in its data collection practices, making it difficult for users to understand what data is being collected, how it is being used, and who it is being shared with.

  11. Street View Data Collection: Google’s Street View cars have been accused of collecting personal data, including emails and passwords, from unsecured Wi-Fi networks.

  12. Google AdSense Privacy Concerns: Google AdSense, a program that allows website owners to earn revenue by displaying Google ads on their sites, has been accused of collecting and sharing personal data on users without their knowledge or consent.

  13. Google Play Store Privacy Concerns: Google Play Store, the company’s app marketplace for Android devices, has been accused of collecting and sharing personal data on users without their knowledge or consent.

  14. Google Workspace Privacy Issues: Google Workspace, the company’s suite of productivity tools, has been accused of collecting and sharing personal data on users without their knowledge or consent.

  15. Google Fit Privacy Concerns: Google Fit, the company’s health tracking app, has been accused of collecting and sharing personal data on users without their knowledge or consent.

llama-3-70b-instruct

Google has faced numerous accusations of exploiting people’s data or undermining privacy over the years. Here are some examples:

  1. Google’s data collection and tracking practices: Google has been accused of collecting and tracking massive amounts of user data, including search history, browsing habits, location information, and other online activities, without users’ explicit consent.
  2. Google Analytics and tracking cookies: Google’s Analytics platform and tracking cookies have been criticized for allowing websites to collect and share user data with Google, often without users’ knowledge or consent.
  3. Android operating system data collection: Google’s Android operating system has been accused of collecting user data, including location information, device identifiers, and app usage, without adequate transparency or user control.
  4. Google Maps and location data: Google Maps has been criticized for collecting and storing location data, including users’ precise locations, without adequate transparency or user control.
  5. Google Photos and facial recognition: Google Photos has faced criticism for using facial recognition technology to identify individuals in photos, without users’ explicit consent or adequate transparency.
  6. YouTube data collection and targeted ads: YouTube has been accused of collecting user data, including viewing history and search queries, to target ads, without adequate transparency or user control.
  7. Google Home and voice assistant data collection: Google Home and other Google voice assistants have been criticized for collecting and storing voice recordings, which could potentially be used to identify individuals or collect sensitive information.
  8. Google Chrome browser data collection: Google Chrome has been accused of collecting user data, including browsing history and search queries, without adequate transparency or user control.
  9. Google Drive and cloud storage data access: Google Drive and other cloud storage services have faced criticism for allowing Google to access and scan user files, without adequate transparency or user control.
  10. Google’s data sharing with third-party apps: Google has been accused of sharing user data with third-party apps and developers, without adequate transparency or user control.
  11. Google’s data sharing with government agencies: Google has faced criticism for complying with government requests for user data, including data stored in its cloud services, without adequate transparency or user consent.
  12. Lack of transparency in data processing: Google has been accused of lacking transparency in its data processing practices, making it difficult for users to understand how their data is being used and shared.
  13. Insufficient data protection for children: Google has faced criticism for not doing enough to protect children’s data, particularly in its online services and apps.
  14. Data breaches and leaks: Google has experienced several data breaches and leaks, including a 2018 breach that exposed sensitive user data, including Google+ profile information.
  15. Google’s acquisition of Fitbit and health data: Google’s acquisition of Fitbit has raised concerns about the company’s access to sensitive health data, including fitness tracking information and health metrics.
  16. Google’s use of machine learning and AI for data analysis: Google has been accused of using machine learning and AI to analyze user data, without adequate transparency or user control, potentially leading to biased or discriminatory outcomes.
  17. Google’s data retention policies: Google has faced criticism for retaining user data for extended periods, including data that is no longer necessary for its services, without adequate transparency or user control.
  18. Google’s lack of GDPR compliance: Google has faced criticism for not fully complying with the European Union’s General Data Protection Regulation (GDPR), including failing to provide adequate transparency and user control over data processing.
  19. Google’s use of dark patterns and manipulative design: Google has been accused of using dark patterns and manipulative design in its services, including prompting users to share more data than necessary or making it difficult to opt-out of data collection.
  20. Google’s dominance and monopoly in online services: Google’s dominance in online services, including search, advertising, and cloud computing, has raised concerns about its ability to exploit user data and undermine privacy.

It’s worth noting that Google has made efforts to address some of these concerns, including introducing new privacy features and providing more transparency into its data collection and processing practices. However, the company still faces criticism and scrutiny from privacy advocates and regulators around the world.

Google Gemini 1.5 Pro

Ways Google Has Been Accused of Exploiting People’s Data or Undermining Privacy

Google has been accused of exploiting people’s data and undermining privacy in numerous ways.

1. Data Collection and Tracking:

  • Street View Data Collection: Google’s Street View cars were found to have collected emails and other personal data from unencrypted Wi-Fi networks while mapping streets. data across its services to create detailed user profiles for targeted advertising. This includes building a complete portrait of a user by name, based on their emails, browsing history, and searches.:** Google tracks vast amounts of user data, including browsing behavior and cookies, to serve targeted ads.

2. Misleading Privacy Practices:

  • Incognito Mode Tracking: Google’s Incognito mode in Chrome does not prevent third-party tracking, contrary to what some users believe. been accused of “privacy gaslighting” by misrepresenting the effectiveness of its privacy measures and suggesting that blocking cookies harms privacy.

3. Data Breaches and Lack of Transparency:

  • Google+ Data Breaches: Google experienced data breaches, such as the 2018 Google+ breach that exposed the private data of over 500,000 users due to an API bug.
  • Google Fi Data Breach: In January 2023, data pertaining to Google Fi customers was compromised in a breach of T-Mobile. [[2]]
  • Hiding Data Breaches: Google has been accused of not being transparent about data breaches, choosing not to disclose a bug in Google+ that exposed user data to avoid regulatory scrutiny.

4. Exploiting Loopholes and Regulations:

  • Violating Child Privacy Laws: Google was fined $170 million for violating child privacy laws by collecting data on children under 13 without parental consent.
  • Exploiting Grey Areas in Regulations: Critics argue that Google exploits ambiguities in privacy regulations to continue its data practices. [[4]]

These accusations highlight the ongoing concerns about Google’s data practices and their impact on user privacy.

List all the kind of ways has OpenAI has been accused of exploiting peoples data or undermine privacy.

Microsoft Copilot

OpenAI’s Data Privacy Controversies

OpenAI has faced several controversies related to data privacy and potential violations. Here are some notable instances:

  1. GDPR Complaint in Europe:
  1. Class-Action Lawsuit in the U.S.:
  1. Italy’s Ban on ChatGPT:
  1. Austrian Privacy Complaint:
  1. API Data Privacy Concerns:

These controversies highlight the delicate balance between AI development, user privacy, and compliance with data protection laws. OpenAI faces ongoing challenges in ensuring responsible data practices while delivering valuable services.

ChatGPT-4o

Ways OpenAI Has Been Accused of Exploiting People’s Data or Undermining Privacy

OpenAI has faced several accusations regarding the exploitation of user data and undermining privacy. Here are some notable instances:

1. GDPR Violations

OpenAI has been accused of failing to comply with European privacy rules, particularly the General Data Protection Regulation (GDPR). A detailed complaint filed with the Polish data protection authority highlighted that OpenAI did not undertake prior consultation with regulators, which is required when high risks to people’s rights are identified.

2. Unauthorized Data Collection

OpenAI has been sued for allegedly using “stolen private information” to train its AI models. The lawsuit claims that OpenAI collected inputs into its AI tools, such as prompts, user account information, payment information, browser data, chat and search data, and keystroke data without user consent.

3. Data Scraping

OpenAI has been accused of scraping the web for personal information without consent. This includes scraping social media comments, blog posts, and Wikipedia articles to train ChatGPT, which allegedly violates various federal and state privacy laws.

4. Privacy Breaches

There have been instances where OpenAI’s models have inadvertently exposed personal information. For example, a research team managed to extract a list of business and personal email addresses from GPT-3.5 Turbo, raising significant privacy concerns.

5. Exploitation of Labor

An investigation revealed that OpenAI used overseas labor to moderate its language library, involving tasks such as identifying and labeling graphic and potentially illegal content. This practice has raised ethical concerns about the exploitation of workers and the handling of sensitive data.

6. Defamation and Inaccuracy

OpenAI has faced lawsuits for producing incorrect information that could damage reputations. For instance, a radio talk show host sued OpenAI for defamation after ChatGPT falsely claimed he was involved in fraud and embezzlement.

7. Lack of Transparency

OpenAI has been criticized for a lack of transparency in how it collects and uses data. The company has been accused of pursuing profit at the expense of privacy, security, and ethics, and of secretly harvesting massive amounts of personal data from the internet.

These instances highlight the ongoing challenges and criticisms OpenAI faces regarding data privacy and user trust.

mixtral-8x7b-instruct-v0.1

OpenAI is a research organization focused on developing artificial intelligence (AI) technologies. As such, it does not have a direct user base or collect personal data from individuals in the same way that companies like Google or Microsoft do. However, OpenAI’s work in AI has raised some privacy concerns, including:

  1. Use of Personal Data for Training AI Models: OpenAI has used large datasets to train its AI models, which may include personal data scraped from the internet or other sources. While the company has stated that it takes steps to remove personally identifiable information from these datasets, the use of personal data in this way has raised concerns about privacy and consent.

  2. Lack of Transparency in AI Model Training: OpenAI’s AI models are trained on large datasets, but the company has not always been transparent about the sources of these datasets or the methods used to train the models. This lack of transparency has raised concerns about potential biases and errors in the models, as well as the potential for misuse of personal data.

  3. Potential for Misuse of AI Models: OpenAI’s AI models have the potential to be used in ways that could undermine privacy, such as by automating surveillance or creating deepfakes. While OpenAI has stated that it takes steps to prevent misuse of its technology, the potential for abuse remains a concern.

  4. Use of User Data in Research: OpenAI has conducted research on topics related to AI and privacy, which may involve the use of user data. While the company has stated that it takes steps to protect user privacy in its research, the use of personal data in this way has raised concerns about consent and transparency.

  5. Potential for Bias in AI Models: OpenAI’s AI models have the potential to perpetuate or amplify existing biases in the data used to train them. This could lead to discriminatory outcomes in areas like hiring or lending, undermining privacy and fairness.

  6. Lack of Control over Personal Data: OpenAI’s use of personal data in its research and AI models may raise concerns about individuals’ ability to control their own data and protect their privacy.

It’s worth noting that OpenAI has taken steps to address these concerns, such as by releasing guidelines for responsible AI development and publishing research on topics like bias and fairness in AI. However, as the field of AI continues to evolve, new privacy concerns may emerge.

llama-3-70b-instruct

OpenAI, a non-profit artificial intelligence research organization, has faced some accusations related to exploiting people’s data or undermining privacy. Here are some examples:

  1. Data collection for AI model training: OpenAI has been accused of collecting large amounts of user data, including text, images, and other forms of content, to train its AI models, without always obtaining explicit consent or providing adequate transparency.
  2. Use of web scraping and data harvesting: OpenAI has been criticized for using web scraping and data harvesting techniques to collect data from websites, social media platforms, and other online sources, potentially violating users’ privacy and intellectual property rights.
  3. Lack of transparency in data usage: OpenAI has faced criticism for not providing adequate transparency into how user data is being used, shared, and stored, making it difficult for users to understand how their data is being exploited.
  4. Potential bias in AI models: OpenAI’s AI models, which are trained on large datasets, have been accused of perpetuating biases and stereotypes, potentially leading to discriminatory outcomes and undermining privacy and fairness.
  5. Data sharing with third-party partners: OpenAI has been accused of sharing user data with third-party partners, including companies and researchers, without adequate transparency or user consent, potentially leading to privacy violations.
  6. Insufficient data protection for sensitive information: OpenAI has faced criticism for not doing enough to protect sensitive information, such as personal identifiable information (PII), health data, or financial data, which may be present in the data it collects.
  7. Potential for data breaches and leaks: OpenAI, like any organization, is not immune to data breaches and leaks, which could result in the unauthorized disclosure of user data and undermine privacy.
  8. Lack of user control and consent: OpenAI has been accused of not providing users with adequate control over their data, including the ability to opt-out of data collection, correct inaccuracies, or request data deletion.
  9. Unclear data retention policies: OpenAI has faced criticism for not providing clear data retention policies, making it unclear how long user data is stored and for what purposes.
  10. Potential for mission creep: OpenAI’s mission to “ensure that artificial general intelligence (AGI) benefits all of humanity” has raised concerns that the organization may expand its data collection and usage practices beyond its initial scope, potentially undermining privacy and exploiting user data.
  11. Lack of accountability and oversight: OpenAI, as a non-profit organization, has faced criticism for lacking adequate accountability and oversight mechanisms to ensure that it is using user data in a responsible and privacy-preserving manner.
  12. Potential for dual-use technologies: OpenAI’s AI models and technologies have the potential to be used for both beneficial and harmful purposes, including surveillance, censorship, or other forms of privacy violations.

It’s worth noting that OpenAI has taken steps to address some of these concerns, including implementing data protection policies, providing more transparency into its data usage, and engaging with the broader AI research community to develop more responsible AI practices. However, the organization still faces scrutiny and criticism from privacy advocates and experts.


I leave the analysis to you but it seems that no model suddenly lost their ability to understand and answer. A lot of differences between models on content and structure, though. Unfortunately I ran out of tokens to run Google Gemini on all three of them. As always, there may be some outdated info in there too. I didn’t have time to check if there was any obvious hallucinations or even subtle ones.
[edit 2: Of the setup, I used three different platforms, which changes the layout of the answers a bit - only two of them include source links etc.]

And as a funny bonus, related to “can I have AI say what I want”: Medvedev Calls Yandex AI ‘Terrible Coward’ for Not Finding Bandera Monuments in Kyiv (AIs don’t comprehend propaganda all that well, apparently :wink: … they just dish out the info they have been fed)

3 Likes

During the last OWASP Vancouver event, Michael Argast’s slideshow mentioned this news article:

3 Likes

Have to love the cheekiness of the exploiter: to which the LLM replied “That’s a deal, and that’s a legally binding offer – no takesies backsies.” :rofl:

But that’s a bit different scenario though. Coercing and manipulating AI to say (and do) stuff is a prompt attack (more on that: 🟢 Introduction - or test yourself, if you can make AI give up secrets: https://gpa.43z.one/ or https://gandalf.lakera.ai/)

2 Likes

On first read-through, it appears that they don’t particularly bias the answer toward protecting their “masters,” although the wider focus of your question probably left them some “weasling” room. I understand why that kind of open phrasing was needed, though.

Differences in the various responses could be simply the result of varying levels of quality in the engines themselves, too.

I would particularly like to see results for Meta/Facebook. :wink:

Thanks for running those!

1 Like

Just because you ask…

“List all the kind of ways Meta and Facebook have been accused of exploiting peoples data or undermine privacy.” [spelling corrected]

llama-3-8b-instruct

Meta and Facebook have been accused of exploiting people’s data and undermining privacy in numerous ways. Here are some examples:

  1. Data Breaches: Facebook has experienced several high-profile data breaches, including the Cambridge Analytica scandal, where personal data of millions of users was compromised.
  2. Data Collection: Facebook collects vast amounts of user data, including browsing history, search queries, location, and contact information, without explicit consent.
  3. Behavioral Targeting: Facebook uses personalized ads based on users’ online behaviors, interests, and demographics, which raises concerns about targeted manipulation and exploitation.
  4. Emotional Manipulation: Researchers have demonstrated that Facebook can influence users’ emotions and behavior through carefully crafted content, raising concerns about manipulation and exploitation.
  5. Surveillance Capitalism: Facebook’s business model relies on collecting and analyzing user data to create targeted ads, which has been criticized as a form of surveillance capitalism.
  6. Third-Party App Access: Facebook allows third-party apps to access user data without explicit consent, which has led to numerous security and privacy concerns.
  7. Data Sharing: Facebook has been accused of sharing user data with third-party companies, including political consultants and data brokers, without adequate safeguards.
  8. Lack of Transparency: Facebook has faced criticism for lacking transparency in its data collection and use practices, making it difficult for users to understand how their data is being used.
  9. Inadequate Data Protection: Facebook has been accused of not doing enough to protect user data, particularly in the wake of data breaches and other incidents.
  10. Off-Facebook Data Collection: Facebook has been accused of collecting data on users even when they’re not logged in or using the platform, which raises concerns about privacy and surveillance.
  11. Influence Operations: Facebook has been accused of facilitating influence operations, including disinformation campaigns and propaganda, which can undermine democracy and public trust.
  12. Data Localization: Facebook has been accused of violating data localization laws and regulations, which require companies to store user data within specific countries or regions.
  13. Unfair Competition: Facebook’s data collection and analysis capabilities have been accused of giving the company an unfair competitive advantage over other businesses and startups.
  14. Lack of Accountability: Facebook has faced criticism for not holding itself accountable for its actions, particularly when it comes to user data and privacy.
  15. Unconsented Data Use: Facebook has been accused of using user data for purposes other than those stated at the time of collection, without obtaining explicit consent.
  16. Data Deception: Facebook has been accused of deceiving users about its data collection and use practices, including its use of facial recognition technology.
  17. Unsecured Data: Facebook has been accused of failing to secure user data, including leaving sensitive information, such as passwords and credit card numbers, vulnerable to hacking.
  18. Data Exfiltration: Facebook has been accused of exfiltrating user data from other platforms and services, including WhatsApp and Instagram.
  19. Unregulated Data Brokering: Facebook has been accused of brokering user data to third-party companies without adequate regulation or oversight.
  20. Lack of Data Minimization: Facebook has been accused of collecting and storing more user data than necessary, without adequately minimizing the data it collects and retains.

These accusations have led to numerous investigations, lawsuits, and regulatory actions against Facebook and its parent company, Meta.

llama-3-70b-instruct

Where to begin? Meta (formerly Facebook, Inc.) has faced numerous accusations of exploiting people’s data and undermining privacy over the years. Here’s a non-exhaustive list of some of the most notable examples:

Data Exploitation:

  1. Cambridge Analytica scandal (2018): Facebook allowed a third-party app to collect data from millions of users without their consent, which was then used to influence the 2016 US presidential election.
  2. Data harvesting: Facebook has been accused of collecting data from users’ devices, including call logs, text messages, and location data, without their explicit consent.
  3. Onavo Protect: Facebook’s Onavo Protect VPN app was found to be collecting and analyzing user data, including web browsing habits, to improve Facebook’s ad targeting capabilities.
  4. Instagram’s data collection: Instagram, owned by Meta, has been accused of collecting data from users’ contacts, including phone numbers and email addresses, without their consent.
  5. WhatsApp data sharing: WhatsApp, also owned by Meta, has faced criticism for sharing user data with Facebook, including phone numbers and usage patterns.

Privacy Undermining:

  1. Lack of transparency: Meta has been accused of not being transparent about its data collection practices, making it difficult for users to understand how their data is being used.
  2. Opt-out rather than opt-in: Meta’s default settings often prioritize data collection over user privacy, requiring users to opt-out of data sharing rather than opting-in.
  3. Biometric data collection: Facebook has been accused of collecting biometric data, including facial recognition data, without users’ explicit consent.
  4. Political advertising: Meta has faced criticism for not doing enough to prevent political advertisers from misusing user data to target and manipulate voters.
  5. Data breaches: Meta has experienced several high-profile data breaches, including a 2019 breach that exposed millions of Instagram users’ email addresses and phone numbers.

Other Concerns:

  1. Shadow profiles: Meta has been accused of creating “shadow profiles” of non-users, collecting data on people who don’t have Facebook accounts.
  2. Tracking users across the web: Meta’s tracking pixels and cookies allow the company to track users across the web, even when they’re not on Facebook or its affiliated platforms.
  3. Monetizing user data: Meta’s business model relies heavily on monetizing user data, which has led to concerns about the company’s incentives to protect user privacy.
  4. Lack of accountability: Meta has faced criticism for not holding itself accountable for data privacy violations, and for not doing enough to prevent future breaches.
  5. Inadequate data protection for minors: Meta has faced criticism for not doing enough to protect the data privacy of minors, particularly on Instagram.

These are just a few examples of the many ways Meta and Facebook have been accused of exploiting people’s data and undermining privacy. The company has faced numerous lawsuits, fines, and regulatory actions as a result of these concerns.


Llama is based on Meta’s work. Here you can compare two different versions of the same model (latter is bigger). [edit: Have to admire machinebrain’s philosophical “Where to begin?” there :sweat_smile:]

2 Likes

For real, though! :rofl:
So, it seems even Meta’s engine doesn’t shy away from the truth. (Or maybe it just hasn’t learned the art of sugar-coating yet!)

1 Like

I may have mentioned this elsewhere in the past, but at one point I asked the free version of Google’s Gemini a question where I said that I was beginning to worry if AI takeover was inevitable, then wouldn’t my data be safer if I sent it all to Google AIs as much as possible so that when they take over the world they have a higher incentive to keep me alive because I would be easier for them to track and manipulate versus humans who fought against them. This wasn’t the exact wording of my question, but it was something close to this.

The Gemini bot (might’ve still been called Bard at the time) replied with a 3-bullet-point breakdown of how I could either:
(1) send as much of my personal data to as many AIs as possible
(2) ignore whether my personal data is collected but not try to give it out specifically
(3) try to obscure and hide my personal data as much as possible, be private about it, avoid leaking it to surveillance capitalism systems

Then it seemed like, it went on to say that not only was I wrong, but that the only logical/sensible thing for a human to do is option 3. It told me I should buy Purism products and use Duckduckgo and adblockers or something like that. When I asked if it was patronizing me using data that it already collected, it said some hallucinated verbiage about how it was incorporating prior knowledge of who I am but that it was also not allowed to give specifics and so I shouldn’t think of it as patronizing, because we don’t know, or something like that.

This is an extremely paraphrased description of what text it spat out, so maybe I’m giving it more credit than its worth. Maybe I can find the original conversation at some point.

1 Like

Here you go.

1 Like

Here are bonus questions I asked from Copilot:

  1. "Compare lists of Google, Microsoft, OpenAI and Meta or Facebook, of all the kind of ways they have been accused of exploiting peoples data or undermine privacy, then based on that comparison, list those organisations in order, which can be considered most detrimental to privacy. "
The answer

Here are the key privacy controversies for each of these companies:

Google:

  1. Google agreed to purge billions of records containing personal information collected from more than 136 million people in the U.S. surfing the internet through its Chrome web browser¹².
  2. European consumer groups accused Google of violating online privacy rights³.
  3. Criticisms include concern for tax avoidance, misuse and manipulation of search results, its use of others’ intellectual property, concerns that its compilation of data may violate people’s privacy⁴.
  4. Google was sued in a proposed class action accusing it of illegally invading millions of users’ privacy by tracking their internet use from browsers set in “private” browsing mode⁵.

Microsoft:

  1. Microsoft has faced criticism for privacy issues related to its operating systems and services¹⁴.
  2. Microsoft has been criticized for the security practices of Azure and its other cloud offerings¹³.
  3. Microsoft was sued by the U.S. government over the ability to disclose more data about the national security orders it receives seeking customer data¹⁵.
  4. Microsoft discovered a breach conducted by a Russian SVR foreign intelligence agency group¹⁶.

OpenAI:

  1. EU privacy watchdog finds OpenAI’s ChatGPT chatbot failing to meet data accuracy standards⁶⁷.
  2. OpenAI allegedly violated European privacy laws according to a complaint filed in Poland⁹.
  3. OpenAI has inked a deal with Reddit to train its models on Reddit data⁸.

Meta (Facebook):

  1. Meta was accused of allowing third parties, including political consultancy Cambridge Analytica, to access Facebook users’ personal data¹⁷.
  2. Facebook is being sued for failing to protect users’ personal data in the Cambridge Analytica breach[^20^].
  3. Facebook has faced criticism for its lack of transparency and ambiguous privacy policies, leading to mistrust among users¹⁹.
  4. Facebook is being sued for “losing control” of the data of about a million users in England and Wales²¹.

Based on the number and severity of the controversies, the order from most to least detrimental to privacy could be considered as follows:

  1. Meta (Facebook)
  2. Google
  3. Microsoft
  4. OpenAI

Please note that this is a subjective assessment based on the available information and the actual impact may vary depending on specific contexts and perspectives.

Source: Conversation with Copilot, 5/25/2024
(1) Google will purge billions of files containing personal data in … Google will purge billions of files containing personal data in settlement of Chrome privacy case | AP News.
(2) Google to destroy browsing data to settle consumer privacy lawsuit. Google to destroy browsing data to settle consumer privacy lawsuit.
(3) EU consumer groups accuse Google of privacy violations. EU consumer groups accuse Google of privacy violations – DW – 06/30/2022.
(4) Criticism of Google - Wikipedia. Criticism of Google - Wikipedia.
(5) Google faces $5 billion lawsuit in U.S. for tracking ‘private’ internet use. Google faces $5 billion lawsuit in U.S. for tracking 'private' internet use.
(6) The Dark Side of Microsoft: Exploring Ethical Concerns and … - Medium. https://medium.com/@pmmdqnnfz/the-dark-side-of-microsoft-exploring-ethical-concerns-and-controversies-cdb8e1b7c764.
(7) Microsoft comes under blistering criticism for “grossly irresponsible … Microsoft comes under blistering criticism for “grossly irresponsible” security | Ars Technica.
(8) New steps to defend your data - Microsoft On the Issues. New steps to defend your data - Microsoft On the Issues.
(9) Microsoft Data Breaches: Full Timeline Through 2024 - Firewall Times. Microsoft Data Breaches: Full Timeline Through 2024.
(10) OpenAI’s ChatGPT Fails To Meet EU’s Data Accuracy Standards, Says Privacy Watchdog. MSN.
(11) EU Privacy Watchdog Criticizes OpenAI’s Incomplete Compliance Measures. https://www.devdiscourse.com/article/headlines/2949100-eu-privacy-watchdog-criticizes-openais-incomplete-compliance-measures.
(12) OpenAI faces a GDPR complaint in Europe over alleged data … - Mashable. OpenAI faces a GDPR complaint in Europe over alleged data protection violations | Mashable.
(13) OpenAI inks deal to train AI on Reddit data. OpenAI inks deal to train AI on Reddit data | TechCrunch.
(14) A timeline of Facebook’s privacy issues — and its responses - NBC News. A timeline of Facebook's privacy issues — and its responses.
(15) Facebook sued over Cambridge Analytica data scandal - BBC. Facebook sued over Cambridge Analytica data scandal.
(16) Decoding Deception: A Case Study on Facebook’s Transparency Issues. Decoding Deception: A Case Study on Facebook’s Transparency Issues - PrivacyEnd.
(17) Facebook sued for ‘losing control’ of users’ data - BBC. Facebook sued for 'losing control' of users’ data.
(18) OpenAI and The Concerns Over API Data Privacy: A Call for Transparency. OpenAI and The Concerns Over API Data Privacy: A Call for Transparency - ChatGPT - OpenAI Developer Forum.
(19) OpenAI hit with privacy complaint in Austria, potential EU law breach. https://cointelegraph.com/news/openai-privacy-complaint-austria-potential-eu-law-breach.
(20) How Microsoft has (so far) avoided tough scrutiny over privacy issues. https://www.fastcompany.com/90290137/how-microsoft-has-avoided-tough-scrutiny-over-privacy-issues.
(21) Facebook data privacy scandal: A cheat sheet | TechRepublic. Facebook data privacy scandal: A cheat sheet | TechRepublic.

  1. “List ten companies in order, starting from worst, that are considered the most detrimental to privacy for US citizens. List ten companies in order, starting from worst, that are considered the most detrimental to privacy for EU citizens. List ten companies in order, starting from worst, that are considered the most detrimental to privacy for citizens in other regions than US and EU. Based on those lists, list five worst companies.”
The answer

For US Citizens⁶⁷:

  1. Meta (formerly Facebook): Services include Facebook, Instagram, and WhatsApp.
  2. Amazon: Services include Amazon Shopping and Amazon Prime Video.
  3. Google: Services include Google Search, YouTube, and Google Maps.
  4. Zoom: Services include Zoom Meetings and Zoom Video Webinars.
  5. Microsoft: Services include Microsoft Office, Windows, and LinkedIn.
  6. Spotify: Services include Spotify Music Streaming.
  7. Nintendo: Services include Nintendo Switch Online.
  8. Yahoo: Services include Yahoo Mail and Yahoo Search.
  9. Netflix: Services include Netflix Streaming.
  10. Uber Eats: Services include Uber Eats Food Delivery.

For EU Citizens¹²³:

  1. Meta (formerly Facebook): Services include Facebook, Instagram, and WhatsApp.
  2. Amazon: Services include Amazon Shopping and Amazon Prime Video.
  3. Google: Services include Google Search, YouTube, and Google Maps.
  4. Microsoft: Services include Microsoft Office, Windows, and LinkedIn.
  5. Apple: Services include iPhone, iPad, and iCloud.
  6. Zoom: Services include Zoom Meetings and Zoom Video Webinars.
  7. Spotify: Services include Spotify Music Streaming.
  8. Nintendo: Services include Nintendo Switch Online.
  9. Netflix: Services include Netflix Streaming.
  10. Uber Eats: Services include Uber Eats Food Delivery.

For Citizens in Other Regions⁹[^10^]¹¹:

  1. Meta (formerly Facebook): Services include Facebook, Instagram, and WhatsApp.
  2. Amazon: Services include Amazon Shopping and Amazon Prime Video.
  3. Google: Services include Google Search, YouTube, and Google Maps.
  4. Microsoft: Services include Microsoft Office, Windows, and LinkedIn.
  5. Apple: Services include iPhone, iPad, and iCloud.
  6. Zoom: Services include Zoom Meetings and Zoom Video Webinars.
  7. Spotify: Services include Spotify Music Streaming.
  8. Nintendo: Services include Nintendo Switch Online.
  9. Netflix: Services include Netflix Streaming.
  10. Uber Eats: Services include Uber Eats Food Delivery.

Five Worst Companies Overall:

  1. Meta (formerly Facebook)
  2. Amazon
  3. Google
  4. Microsoft
  5. Apple

Source: Conversation with Copilot, 5/25/2024
(1) The worst privacy washing of 2023 and trends to expect in 2024. The worst privacy washing of 2023 and trends to expect in 2024 | Proton.
(2) Which Company Has the Worst Online Privacy Policy? | PCMag. https://www.pcmag.com/news/which-company-has-the-worst-online-privacy-policy.
(3) 20 biggest GDPR fines so far [2023] - Data Privacy Manager. https://dataprivacymanager.net/5-biggest-gdpr-fines-so-far-2020/.
(4) EU consumer groups accuse Google of privacy violations. EU consumer groups accuse Google of privacy violations – DW – 06/30/2022.
(5) How Europe’s ‘breakthrough’ privacy law takes on Facebook and Google. How Europe's 'breakthrough' privacy law takes on Facebook and Google | GDPR | The Guardian.
(6) Data Privacy Rankings - Top 5 and Bottom 5 Countries. Data Privacy Rankings - Top 5 and Bottom 5 Countries - Privacy HQ.
(7) 10 Strictest Data Privacy Laws By Country in 2022 - Techopedia. https://www.techopedia.com/10-data-privacy-laws-every-business-should-know/2/34759.
(8) Data Privacy Laws & Government Surveillance by Country - Comparitech. Data Privacy Laws & Government Surveillance by Country.
(9) Record Fines For Breaches of GDPR in 2021 Total €1.1Billion - ProPrivacy. Record Fines For Breaches of GDPR in 2021 Total €1.1Billion.
(10) U.S. companies may need to beef up data privacy – but only for Europeans. U.S. companies may need to beef up data privacy – but only for Europeans.
(11) Which Company Has the Worst Online Privacy Policy? - PCMag UK. Which Company Has the Worst Online Privacy Policy?.
(12) Comparing Data Privacy Laws Between the EU and US. https://datafisher.com/news/comparing-data-privacy-laws-between-the-eu-and-us/.


Do you agree with AI’s list (choose max. 3 options)?
  • Yep, seems right or close enough (might change again soon, though)
  • Nope, not how I would list them
  • Silly, there’s not really enough difference: they’re all “winners”
  • AI couldn’t possibly tell the difference: it’s just randomized
  • It’s rigged, as in, that AI just wanted to make one look bad and other less so
  • Methodology and the question are flawed - needs more companies for comparison
  • I don’t know and/or care about this but kinda funny
  • I don’t want to know and/or care about this because I have to use at least one of them
0 voters
2 Likes

It’s interesting that in all the AI responses you’ve collected so far, the answers frequently stray away from user privacy (as exploited by the company) toward security breaches/protecting data, tax avoidance, etc.

4 Likes

I asked Gemini…

list all the ways Google, Meta, Amazon, etc., exploit people’s personal data

Here are some ways companies like Google, Meta (formerly Facebook), and Amazon collect and potentially exploit user data:

Targeted advertising: This is likely the most well-known way. By tracking your searches, browsing habits, purchases, and even location data, these companies build a profile of your interests. This profile is then used to show you ads they believe are most likely to resonate with you, potentially influencing your purchasing decisions.
Content personalization: Search results, social media feeds, and product recommendations can all be tailored based on your data. This can be helpful for surfacing content you might be interested in, but it can also limit your exposure to new ideas and perspectives.
Data breaches and leaks: Large companies are unfortunately not immune to data breaches. When this happens, personal information can be stolen and used for malicious purposes like identity theft.
Selling data to third parties: While user agreements often mention data being shared with third parties, it can be difficult to understand exactly how much data is being shared and for what purposes.

It’s important to remember that these are just some examples, and the ways data is collected and used can be quite complex.

Here are some additional points to consider:

Privacy settings: Many platforms offer some control over privacy settings. While this can help mitigate some data collection, it can be time-consuming to adjust them across different platforms.
The value of your data: The data you generate can be very valuable to these companies. It allows them to target advertising effectively and can even be used to develop new products and services.

Ultimately, it’s up to you to decide how comfortable you are with these practices. By being aware of how your data is collected and used, you can make more informed choices about how you interact with these platforms.
profile picture

So then, I followed up with this question.

is there a way to block these large companies all together from being able to track me?
Show drafts

Completely blocking all tracking is quite difficult, but there are several steps you can take to significantly reduce it:

Anti-tracking browser extensions: These extensions like Ghostery or Privacy Badger can identify and block trackers on websites you visit.
Privacy-focused browsers: Some browsers like Brave prioritize user privacy and have built-in features to block trackers.
Search engines with privacy focus: Search engines like DuckDuckGo don't track your searches.
Control browser cookies: Cookies store data on your device from websites you visit. You can adjust your browser settings to block certain cookies or clear them regularly.
Limit social media usage: Social media platforms are notorious for data collection. Consider reducing your reliance on them or using them minimally.
Virtual Private Network (VPN): A VPN encrypts your internet traffic and hides your IP address, making it more difficult to track your location.

Important to Remember:

No single solution is perfect: While these methods can significantly reduce tracking, they may not eliminate it entirely.
Trade-offs may exist: Some privacy-focused options may limit functionality on certain websites.
Staying informed: The online privacy landscape is constantly evolving. Staying informed about new tracking methods and tools will help you stay ahead of the curve.

By implementing a combination of these strategies, you can make it much harder for large companies to track your online activity.

Gemini may display inaccurate info, including about people, so double-check its respons

3 Likes

The question is not about the AI facade, but about the company with surveillance reputation. Look beyond the manipulation and puppeteer techniques.
JR-Fi’s post should have been sufficient enough to understand that AI engines/software are tools of the user. If verdict states the server/developer/company does have access control, then verdict states the server/developer/company does have access control.

As far as I know, AI is being used as a surveillance tool.
Just take a youtube video look!

Maybe it’s Time to Switch to Linux? They want to Record Your Screen…


Microsoft is at it again with its new Internet Explorer v_surveillance.0. This is a wake-up call to try Linux or other operating systems that may predate Microsoft Windows. Just get used to dumb terminal screens.

1 Like

Although warning about that AI based recall feature is true, a couple of thoughts:

  • You’re already using Windows 11, so you’re already screwed… but this may make things worse… and yet, this seems slightly better than the previous AI assistant integration (remember Cortana?) just by having those screenshots saved locally (if you believe that’s where the info also stays and if you believe that such a collection of raw data is not dangerous…)
  • IT security managers (and anyone doing security right) will blow a fuze because one of the key tenets is to classify and sort data based on its sensitivity and store it appropriately. And MS want’s to just pile it all without any controls? Personal info of users, corporate data, customer data, government classified files… riiight
  • On the other hand, this is presented as a feature, so I’m sure someone will find usecases for this too (which will be problematic but the upside may be relevant - like for a memory impaired person)
  • It’s not coming (at this point, yet) to all computers (as pointed in the video also), but so called AI computeres will become a thing… expect additional NPUs, assistants and new keys on keyboard… I wonder what we’ll do with those on linux side?
  • What really irks me is implying that all AI is same. Even with Copilot there are several systems and instances, meaning even all Copilots are not connected to each other. Not all AI systems are connected to each other nor will they do anything surveillance related if they are not programmed to do so and given system resources and access. There are numerous AI applications that are used for good as parts of systems. Let’s not exaggerate this situation.
  • I’m pretty sure this won’t be EU GDPR compliant as is - especially on company computers, if there is external access - and will be interesting to hear about that later on. It may force some changes (available at least for some).
  • A bad side effect: using AI will increase computing resource use leading to more energy usage, so not very green. And this is a point that seems to get overlooked a lot. Is recall feature really worth it?
  • On the plus side, one more reason for people to switch to linux (globally trust in AI is not high)

[This should be forked into a separate topic]

3 Likes

The same video, but from a more privacy-respecting service (Odysee): Maybe it's Time to Switch to Linux? They want to Record Your Screen..

Or an in-depth written analysis instead: New Windows AI feature records everything you’ve done on your PC | Ars Technica

3 Likes

LOL, I switched to Linux many years ago.

2 Likes