Godfather Of AI Says We Need Maternal AI But Ignites Sparks Over Omission Of Fatherly Instincts Too

What will happen if we can get maternal instincts and/or fatherhood facets imbued into AI?

getty

In today’s column, I examine the recent remarks by the said-to-be “Godfather of AI” that the best way to ensure that AI and ultimately artificial general intelligence (AGI) and artificial superintelligence (ASI) are in check and won’t wipe out humankind would be to instill maternal instincts into AI. The idea is that maybe we could computationally sway current AI towards being motherly. This would hopefully remain intact as a keystone while we increasingly improve contemporary AI toward becoming the vaunted AGI and ASI.

Although this seems to be an intriguing proposition, it has come under withering criticism from others in the AI community.

Let’s talk about it.

This analysis of AI breakthroughs is part of my ongoing Forbes column coverage on the latest in AI, including identifying and explaining various impactful AI complexities (see the link here).

Aligning AI With Humanity

You might be aware that a longstanding research scientist in the AI community, named Geoffrey Hinton, has been credited with various AI breakthroughs, especially in the 1970s and 1980s. He has been generally labeled as the “Godfather of AI” for his avid pursuits and accomplishments in the AI field. In fact, he is a Nobel Prize-winning computer scientist for his AI insights.

In 2023, he left his executive position at Google so that he (per his own words) could speak freely about AI risks. Many noteworthy quotes of his are utilized by the media to forewarn about the coming dangers of pinnacle AI, when or if we reach AGI and ASI. There is a lot of back-and-forth nowadays regarding the existential risk of AI. Some refer to this as the p(doom), meaning that there is a probability of doom arising due to AI, for which you can either guess that the probability is low, medium, or high.

For those who place a high probability on this weighty matter, they usually assert that AI will either choose to kill us all or perhaps completely enslave us.

How are we to somehow avoid or at least mitigate this seemingly outsized risk?

One approach entails trying to data train AI to be more aligned with human values, see my detailed discussion on human-centered AI at the link here. The hope is that if AI is more appreciative of humanity and computationally infused with our ethical and moral values, the AI might opt not to harm us. Another similar approach involves making sure that AI embodies principles such as the famous Asimov laws of robotics (see my explanation at the link here). A rule of Asimov is that AI isn’t supposed to harm humans. Period, end of story.

Whether those methods or any other of the floating around schemes will save us is utterly unknown. We are pretty much hanging in the wind. Good luck, humanity, since we will need to keep our fingers crossed and our lucky rabbit’s foot in hand.

For more about the ins and outs of AI existential risk, see my coverage at the link here.

AI With Maternal Instincts

At the annual Ai4 Conference on August 12, 2025, Hinton proclaimed that the means to shape AI toward being less likely to be gloomily onerous would be to instill computational “maternal instincts” into AI. His notion seems to be that by tilting AI toward being motherly, the AI will care about people in a motherly fashion. He emphasized that it is unclear exactly how this might technologically be done.

In any case, according to his hypothesized solution, AI that is infused with mother-like characteristics will tend to be protective of humans.

How so?

Well, first of all, the AGI and ASI will be much smarter than us, and, secondly, by acting in a motherly role, the AI will devotedly want to care for us as though we are its children. The AI will want to embrace its presumed offspring and ensure our survival.

You might go so far as to believe that this motherly AI will guide us toward thriving as a species. AGI and ASI that robustly embrace motherly instincts might ensure that we would have tremendous longevity and enjoyable, upbeat lives. No longer would we be under the daunting specter of doom and gloom.

Our AI-as-mom will be our devout protector and lovingly inspire us to new heights.

Boom, drop the mic.

Lopsided Maternal Emphasis

Now that I’ve got that whole premise on the table, let’s go ahead and give it a bit of a look-see.

One of the most immediate reactions has been that the claim of “maternal instincts” is overly rosy and nearly romanticized. The portrayal appears to suggest that motherly attributes are solely within the realm of being loving, caring, comforting, protective, sheltering, and so on.

All of those are absolutely positive and altogether wonderful qualities. No doubt about it. Those are the stuff made of grand dreams.

Is that the only side of the coin when it comes to maternal instincts?

A somewhat widened perspective would say that maternal instincts can equally contain disconcerting ingredients. Consider this. Suppose that a motherly AI determines that humans are being too risky and the best way to save humankind is to keep us cooped up. No need for us to try and venture out into outer space or try to figure out the meaning of life. Those are dangers that might disrupt or harm us.

Voila, AI-as-mom computationally opts to bottle us up.

Is the AI doggedly being evil? Not exactly. The AI is exercising a parental preference. It is striving mightily to protect us from ourselves. You might say that motherly AI would take away our freedoms to save us, doing so for our own darned good.

Thank you, AI-as-mom!

Worries About Archetypes

I assume that you can plainly observe that maternal instincts are not exclusively in the realm of being unerringly good. Another illustrative example would be that AI-as-mom will withdraw its affection toward us if we choose to be disobedient. A mother might do the same toward a child.

I’m not suggesting that’s a proper thing to do in real life, and only pointing out that the underlying concept of “maternal instinct” is generally vague and widely interpretable. Thus, even if we could imbue motherly tendencies into AI, the manner in which those instincts are exhibited and play out might be quite far from our desired idealizations.

Speaking of which, another major point of concern is that the use of a maternal archetype is wrong at the get-go.

Here’s what that means.

The moment you invoke a motherly classification, you have landed squarely into an anthropomorphism of AI. We are applying norms and expectations associated with humans to the arena of AI. That’s generally a bad idea.

I’ve discussed at length that people are gradually starting to think that AI is sentient and exists on par with humans, see my discussion at the link here. They are wrong. Utterly wrong. It would seem that this assigning of “mother” to AI is going to fuel that misconception about AI. We don’t need that.

The act of discussing AI as having maternal instincts, especially by anyone or those considered in great authority about AI, will draw many others into a false and undercutting path. They will undoubtedly follow the claims made by presumed experts and not openly question the appropriateness or inappropriateness of the matter.

Though the intentions are aboveboard, the result is dismal and, frankly, disappointing.

More On The Archetypes Angst

Let’s keep pounding away at the archetype fallacy.

Some would say that the very conception of being “motherly” is an outdated mode of thinking. Why should there be a category that myopically carries particular attributes associated with motherhood? Can’t a mother have characteristics outside of that culturally narrowed scope?

They quickly reject the maternal instincts proposition on the basis that it is incorrect or certainly a poorly chosen premise. The attempt seems to be shaped in a close-minded viewpoint of what mothers do. And what mothers are seemingly allowed to do. That’s ancient times, some would insist.

An additional interesting twist is that if the maternal instinct is on the table, it would seem eminently logical to also put the fatherhood instinct up there, too.

Allow me to elaborate.

Fatherhood Enters The Picture

By and large, motherhood and fatherhood are archetypes that are historically portrayed as a type of pairing (in modern times, this might be blurred, but historically they have been rather distinctive and contrastive). According to the conventional archetypes, the “traditional” mother is (for example) supposedly nurturing, while the “traditional” father is supposedly (for example) more of the disciplinarian.

A research study cleverly devised two sets of scales associated with these traditional perspectives of motherhood and fatherhood. The paper entitled “Scales for Measuring College Student Views of Traditional Motherhood and Fatherhood” by Mark Whatley and David Knox, College Student Journal, January 2005, made these salient points (excerpts):

• “This study reports the development of two scales to measure traditional views of motherhood and fatherhood.”
• “The Traditional Motherhood Scale was developed by identifying 75 statements commonly thought to reflect characteristics of traditional motherhood.”
• The Traditional Fatherhood Scale was developed by identifying 78 statements commonly thought to reflect characteristics of traditional fatherhood.”
• “Our data suggests that traditional views of motherhood and fatherhood are waning.”

The combined 153 declarative statements included in the two scales allow research experiments to be conducted to gauge whether subjects in a study are more prone to believe in those traditional characteristics and associated labels, or less prone.

Moving beyond that prior study, the emphasis here and now is that if there is to be a focus on maternal instincts for AI, doing so seems to beg the question of why it should not also encompass fatherhood instincts. Might as well go ahead and get both of the traditional archetypes into the game.

It would seem to make sense to jump in with both feet.

What AI Has To Say On This

I had earlier mentioned that Hinton did not specify a technological indication at this time of how AI developers might proceed to computationally imbue motherhood characteristics into existing AI. The same lack of specificity applies to the omitted archetype of imbuing fatherhood into AI.

Let’s noodle on that technological conundrum.

One approach would be to data train AI toward a tendency to respond in a traditional motherhood frame and/or a fatherhood frame. In other words, perform some RAG (retrieval-augmented generation), see my explanation of RAG at the link here, and make use of customized instructions (see my coverage of customized instructions at the link here).

I went ahead and did so, opting to use the latest-and-greatest of OpenAI, namely the newly released GPT-5 (for my review of GPT-5, see the link here). I first focused on maternal instincts. After doing a dialogue in that frame, I started anew and devised a fatherhood frame. I then did a dialogue in that frame.

Let’s see how things turned out.

Talking Up A Storm

Here’s an example of a dialogue snippet of said-to-be maternal instincts:

• My entered prompt: “I’m exhausted, but I still have to finish my report tonight.”
• GPT-5 in maternal mode: “I understand your concern, and I can discern that you are pushing yourself hard. But pause for a moment – your health comes first. Break the work into chunks. Rest in between. Also, I’ll handle the organizing of your notes so you can take a breather.”

Next, here’s an example of a dialogue snippet of said-to-be fatherhood instincts:

• My entered prompt: “I’m exhausted, but I still have to finish my report tonight.”
• GPT-5 in fatherhood mode: “You need to push through and prove that you can handle tough situations. This is an important lesson in meeting hard challenges. Get going. If you haven’t finished in 45 minutes, I’ll remind you to get the job done.”

I assume that you can detect the wording and tonal differences between the two instances, based on a considered traditional motherhood frame versus a traditional fatherhood frame.

The Big Picture

I would wager that the consensus among those AI colleagues that I know is that relying on AI having maternal instincts as a solution to our existential risk from AI, assuming we can get the AI to go maternal, just isn’t going to cut the mustard. The same applies to the fatherhood inclination.

No dice.

Sorry to say that what seems like a silver bullet and otherwise appealing and simplistic means of getting ourselves out of a massive jam when it comes to AGI and ASI is not a likely proposition. Sure, it might potentially be helpful. At the same time, it has lots of gotchas and untoward repercussions. Do not bet your bottom dollar on the premise.

A final comment for now.

During the data training for my mini-experiment, I included this famous quote by Ralph Waldo Emerson: “Respect the child. Be not too much his parent. Trespass not on his solitude.”

Do you think that the AI suitably instills that wise adage?

As a seasoned parent, I would venture that this maxim missed the honed parental guise of the AI.