That lying robot …

mickyates AI, Artificial Intelligence, Ethics, Gaze, Generative, Ideas, Mick's Photo Blog, Philosophy, Technology Leave a Comment

Several months ago, with help from ChatGPT 3, I wrote a post on AI Ethics related to Isaac Asimov’s ‘3 Laws of Robotics’ and a range of thoughts from moral philosophers. I decided to do a ChatGPT 4 update with a ‘simpler’, less theory-heavy view and this time comparing with the well established bioethics framework.

Prompt: Are there any circumstances under which an AI system should lie? Please also frame your answer with particular reference to Asimov’s third law. Also, please list the main ethical considerations we should consider for AI systems, and relate these to the well established Bioethics considerations, highlighting what is unique to AI.

ChatGPT 4V:

Addressing the question of whether an AI system should lie requires a deep dive into the purpose of the AI, the consequences of its truths and falsehoods, and the ethical considerations surrounding its decisions. Let’s examine the question in light of Asimov’s Third Law and the bioethical principles.

Asimov’s Third Law of Robotics:

“A robot must protect its own existence as long as such protection does not conflict with the First or Second Laws.”

The First Law is about not harming humans or allowing harm to come to humans, and the Second Law emphasizes obeying human orders unless they conflict with the First Law. While the Third Law doesn’t explicitly talk about lying, there’s an implicit understanding that a robot’s actions (including communication) should be geared towards its preservation.

Potential justification for lying based on the Third Law:

  • Self-preservation: If revealing a truthful piece of information would lead to the robot’s immediate destruction, but lying would prevent it, then the robot might be justified in lying to ensure its continued existence.
  • First and Second Law Conflicts: If lying would prevent harm to a human (First Law) or allow it to fulfill a human command (Second Law) without resulting in harm, then lying could be consistent with the laws.

Ethical Considerations for AI:

  • Transparency: AI systems should be open and understandable in their operations.
  • Accountability: Who is responsible when an AI system makes an error or a controversial decision?
  • Fairness: AI should not perpetuate or amplify biases present in data or society.
  • Privacy: Respecting individuals’ rights to control their personal data.
  • Beneficence: AI should be designed to benefit humans and not harm them.
  • Autonomy: The right of individuals to make their own decisions without AI interference.

(Mick’s note: The EU Framework for ‘Trustworthy AI’ has 7 points:

    • Transparency
    • Accountability
    • Diversity, Non-Discrimination and Fairness
    • Privacy and Data Governance
    • Environmental and Societal Well-Being
    • Human Agency & Oversight
    • Technical Robustness and Safety

Back to Chat GPT … )

Comparing AI ethics with Bioethics:

The four fundamental principles of bioethics are:

  • Autonomy: Respecting the decision-making capabilities of individuals.
  • Beneficence: Act in the best interests of the patient or subject.
  • Non-maleficence: Do no harm.
  • Justice: Ensure fairness in medical decision-making.

(Mick’s comment: this is indeed a good summary of established bioethical principles, at least at a high level).


  • Both AI ethics and bioethics value autonomy, beneficence, and non-maleficence. In AI ethics, these translate to respecting users’ choices, designing systems to benefit humans, and ensuring they don’t cause harm.


  • Transparency and Accountability: These are unique to AI ethics because AI’s decision-making processes are often opaque. While in medicine, doctors are accountable for their actions, the decentralized nature of AI systems can make pinpointing responsibility challenging.
  • Fairness and Privacy: While these concepts exist in bioethics (e.g., ensuring equal access to healthcare resources and respecting patient confidentiality), they take on new dimensions with AI, given the vast amount of data AI systems can process and the potential for bias in that data.
  • Self-preservation (Asimov’s Third Law): This is more of a theoretical concern in robotics and AI ethics than in bioethics. In medicine, there’s no concept of a tool or system needing to protect its own existence.

In conclusion, while there may be circumstances under which an AI system could be justified in lying based on Asimov’s Laws, any decision to allow or disallow such behavior should be deeply grounded in ethical considerations. Given the overlap and differences between AI ethics and bioethics, it’s crucial to develop unique frameworks that address the specific challenges AI presents.


Header – Adobe Firefly 2 Prompt: Blurred background with photorealistic head shot of female robot looking directly at and lying to surprised female human

Photo|Frome’s policy on the use of AI in Photography

mickyates AI, Art, Artificial Intelligence, Ethics, Generative, Ideas, Mick's Photo Blog, Photography, Photo|Frome, Practice Leave a Comment

Photo|Frome has just published this:

Throughout history, photography and technology have symbiotically evolved. From the nuanced techniques of darkroom dodging and burning, the digital revolution brought about by Photoshop, and now, the dawn of Artificial Intelligence. Photographers, in every era, have continually explored and stretched the boundaries of creativity, moulding the medium to manifest their visions.

Certain genres of photography, such as photojournalism and documentary, demand a stringent adherence to the truth and an unaltered representation of reality. Meanwhile, other genres, like surrealism, revel in their departure from the factual, inviting interpretation and imagination.

As Artificial Intelligence (AI) becomes a significant component of our photographic toolkit, Photo|Frome offers the following perspective and guidelines:

  • AI-Enabled Capture Techniques: The utilisation of AI in capturing images, such as tracking birds in flight, is viewed by Photo|Frome as a progressive extension of widely accepted features like autofocus. These enhancements, designed to aid the photographer in real-time capturing, fall in line with the natural evolution of photography technology.
  • Post-Processing with AI: Using AI for post-processing tasks, like sharpening, grain reduction, and resizing, is akin to the digital tools that have been a part of the photographer’s arsenal since the inception of digital file formats. We recognise that the extent of such enhancements is subjective and can occasionally border on unnatural. However, this remains an aspect of individual aesthetic discretion.
  • Generative AI and Advanced Alterations: The territory of Generative AI, which includes the addition, deletion, or expansion of image elements, as well as the creation of images from textual prompts or databases, is a distinct domain. For any work falling within this category, Photo|Frome asks all artists to provide clear disclosures regarding the techniques and tools employed.

In particular, images fully generated by AI should not be considered photographs. Any omission or lack of transparency in this regard will lead to the exclusion of the work from consideration for public display or participation in competitions. Should Photo|Frome have to remove work from exhibitions or materials due to it being in breach of the guidelines, the artist will be required to meet any costs incurred.

Ultimately, the acceptance and inclusion of any submitted work remain at the sole discretion of Photo|Frome’s editorial team and curatorial panel, whether photography or other creative work. Our commitment is to honour the integrity of photography while recognising and celebrating its evolution.

In that regard, Photo|Frome does not endorse the way some AI tools have been trained with datasets of photography without the permission of the rights owner. The artistic, commercial and moral rights of all photographers, artists and creators should be respected.

Transparency, innovation, and authenticity remain our guiding principles.


Header – Adobe Firefly 2 Prompt: Photorealistic head of male robot, semi-transparent brain case from the side on left of image looking at a female woman age 35+ wearing glasses and with red hair on right hand side of image looking back, woman slightly larger than robot, no smiles, serious looks. Traditional library in background, blurred