AI Can Improve Great Lawyers—But It Can’t Replace Them

June 2, 2025

Ralph Losey, June 2, 2025.


The rise of legal AI has sparked a familiar fear: that our hard-won expertise might be absorbed into machines. That lawyers will be off-loaded—our reasoning encoded, commodified, and reduced to prompts. That we’ll be sidelined into “hand-holding” roles—providing comfort more than cognition, reassurance instead of reasoning. Or worse, that we’ll be replaced altogether.

Click to see video by Losey and his AIs, primarily Sora.

These anxieties are understandable. But they rest on a flawed premise: that all legal judgment can be captured, transferred, and automated. I’ve long disagreed. This article lays out why and how AI, when properly harnessed, can amplify human lawyers rather than erase them.

One recent LinkedIn post by Damien Riehl distilled this anxiety into what he called “the trillion-dollar question;” how firms capture—and try to monetize—lawyerly know-how. His reflection was a catalyst for this piece. But the ideas here reflect a position I’ve long held: AI can assist, but it cannot replicate the highest levels of legal reasoning. The future of the profession depends on knowing the difference and building systems that keep humans in the lead.

Image by Losey using Sora AI.

Introduction

The foundational fear behind AI replacement anxiety is based on a flawed assumption: that all of a lawyer’s judgment can be taught to a machine. Some of it can, no question. But the most valuable parts—the creative, emergent, contextual decisions—cannot. Legal expertise isn’t just about rules. It’s about timing, presence, and insight.

Damien Riehl recently posted on LinkedIn what he calls “the trillion-dollar question,” asking how firms value—and try to bottle—lawyerly know-how. His post included this insightful prompt and infographic:

“The trillion-dollar question: What is human judgment’s monetary value? 🤷 If a firm wants that lawyer’s know-how — to place it in an artifact (e.g., knowledge base), will that lawyer give it up for free (no additional compensation)? Especially if the lawyer is considering jumping ship — to Firm #2? Or will Firm #1 need to pay that lawyer for that scarce resource: know-how? After all, as hashtag#Tasks get commoditized (see Agents), then that lawyer’s human expertise/judgment is among the only hashtag#value left.

Image by Damien Riehl.

Damien is right to highlight scarcity. But I would frame it this way: the most valuable legal knowledge isn’t just scarce—it’s uniquely human and inalienable.

When I replied to Damien’s post, I put it simply:

“I don’t think lawyers need to worry. The truly valuable knowledge cannot be ingested by AI.”

A good discussion ensued pro and con. This article is the elaboration on my position.

Click for Video by Losey of future AI enhanced law office.

The Basic Point of Disagreement

Let me start by saying I agree with Damien—up to a point. Much of what lawyers do can be absorbed and automated. The boring stuff. The repetitive stuff. The kind of tasks that make you question your life choices—zero creativity, minimal judgment required. AI can do that. And should.

I say: good riddance.

I’ve billed for thousands of hours in that rut. But the stuff I stayed for—the creativity, the improvisation, the intuitive leaps—that part cannot be transferred to AI. That’s the scarce resource. The irreplaceable trillion-dollar bit.

Let me put it this way, just off the cuff: the most valuable human knowledge in law, or in any complex domain, cannot be input into AI because it is spontaneously created on an ongoing basis by humans from out of the particular ever-changing space-time configurations. It is ever-changing. AI needs human experts. It must remain a hybrid relationship.

Click to see video by Losey.

Each case, client, judge, and moment is distinct. I’ve handled a thousand legal matters since 1980, and no two have been exactly alike. None had the exact same facts, the same players, the same pressures. There are patterns, yes—but they aren’t circular. They spiral forward. Like DNA, legal reasoning evolves in loops that never exactly repeat. There’s structure, but the content within the structure is dynamic.

The best lawyers are not rote technicians—they are improvisational strategists. We may start with templates, but we do not end there. Only Gilbert-style lawyers (remember those law school simplifications?) are replaceable.

Systematic Three-Part Argument for Irreplaceability

To bring structure to this argument, I called in two of my favorite collaborators: old ChatGPT-4o (Omni) for wordsmithing, and the new state-of-the-art SORA for image generation. I prompted, shaped, edited, and reimagined—then fused their outputs with my own reasoning. That process itself is a case in point: Human-AI collaboration where the human has final control. Sometimes that’s not easy because AI can seem human and be hard to pin down.

What happened to my AI? Images by Losey. Click here to see video.

1. Human Knowledge Is Contextual and Emergent

The most valuable legal knowledge is not reducible to rules. It emerges in context—during a tough deposition, in a late-night drafting session, in the moment you stand to speak, when you think on your feet to respond to the unexpected.

This kind of knowledge:

  • Is not static (like statutes),
  • Is always evolving,
  • And is grounded in specific moments of time, place, and interaction.

AI lacks access to the now. It doesn’t live in our space-time. It doesn’t feel when a witness is off. It cannot read a room, has no empathy, intuition, or gut instinct.

What AI can do is amazing but this awareness should be balanced by knowledge of its limitations. This is the theme of the 100 + articles I’ve written on generative AI since 2023. See e.g., The Human Edge: How AI Can Assist But Never Replace (01/30/25). The writings are based on my personal use of generative AI since 2023 and long experiences as a lawyer and first user of other new technologies. There are always dangers in new technologies, but the elimination of legal practice is not one of them, not even with AGI or superintelligence.

Our intelligence is unique and dynamic. It arises anew each day like the Sun, emerging from the interplay of perception, emotion, intuition, and inspiration. AI has none of this. It is like the Moon that reflects the Sun’s light. All it can do is think.

Click here to see video by Losey on YouTube.

2. The Epistemological Limits of AI in Law

There is an boundary to what AI can know and understand. AI can simulate knowledge (e.g., predict patterns based on precedent), but it cannot originate genuine understanding or creative insight within a specific, real-world context. It lacks consciousness, lived experience, and embodied awareness—core faculties that human lawyers use to reason through complex legal and ethical challenges.

AI is like a brilliant parrot with a photographic memory—but no inner life.

Click to see Ralph’s full illustration on YouTube.

I’m a strong proponent of AI, but I temper that enthusiasm with something I call ontological humility. “Ontology” deals with the nature of being, what something truly is, not just how it behaves. And that’s the key. AI may look smart and sound persuasive, but it doesn’t know anything. It predicts and correlates; it doesn’t understand or care. Judgment requires presence, experience, and agency, things AI doesn’t possess. That’s why the human must remain in charge.

3. Hybrid Multimodal Systems: A Proven Model for the Future

Because of these limits, I have always advocated for hybrid human-AI systems. Not just in theory, but in method. Starting with e-discovery in 2012, I developed what I called Hybrid Multimodal approaches.

In that context, it meant combining:

  • Predictive coding (active machine learning),
  • Boolean keyword search,
  • Concept search,
  • Linear review,
  • And—most importantly—human creativity and supervision.

Why? Because no two discovery projects are alike. And no one method suffices. The strength comes from the interplay. See the free online course I made to share the hybrid multimodal method of document review. Here is a montage of illustrations for the course prepared by Losey just using PhotoShop.

Now, in the generative AI era, Hybrid Multimodal means something broader and, for me at least, much more interesting:

  • Human plus machine;
  • Text plus image, plus video, plus sound;
  • Prompts plus visualization, plus spontaneous human improvisation in chats; and,
  • Technical, architectural design and training processes, inside the AI itself.

This last listed technical meaning of “multimodal” is new. It isn’t about how users interact with the tools—it’s about how the models are built, how they fuse the different types of data. The new AIs are designed to facilitate multimodal. Users of AI do not need to know how AI integrates multiple data types, but for the insanely curious, see the review of Li and Tang,Multimodal Alignment and Fusion: A Survey (arXiv, Nov. 2024) (overview of how today’s AI systems align and combine text, images, audio, and video to generate richer, more context-aware outputs.)

Below are several infographic-style images prepared by ChatGPT-4o based on the text in the last two paragraphs. They visualize what AI hybrid multimodal today means, both in the way users may interact with it and in algorithmic and training work required to fuse the data so that this is possible. These graphics thus both demonstrate this text-image fusion, and, at the same time, explain it.

Even when I already know the answer, if it’s important, I may still ask for AI input. Why? Because it sees patterns across all fields. It’s a polymath. I’m not. I use it to stretch my thinking—to see the connections I might have missed.

I know some small part of the law. AI knows everything else. That’s a powerful partnership; again, so long as we remember who’s in charge. In the future, our robots will carry the bags, just like the starting associates of old.

Click here to make image come alive. AI photo by Losey.

Conclusion

The legal profession is not facing extinction by AI. It’s facing transformation through augmentation. The question is not whether AI will replace lawyers, but which lawyers will harness AI to amplify their judgment, and which will delegate themselves into irrelevance. That is the trillion-dollar question facing all of humanity, not just lawyers.

Just how valuable and unique is the human brain? Image by Losey. Click for his YouTube video.

Law’s highest-value knowledge is not static. It is situational, contextual, and alive. It emerges through human presence, experience, and discretion. No model, no matter how large, can replicate what happens in the mind of a skilled advocate adapting in real time to a novel legal problem.

AI can help us see patterns, accelerate production, and surface insights. But it cannot stand in our shoes. The future of legal excellence lies not in human replacement, but in human-AI synergy. That future is hybrid. That future is multimodal. That future is already here.

Click here for video animation by Losey

Each time you interact with advanced AI the experience is different. Sometimes what happens is surprising and leads to improvements in both quality and productivity. Click the same graphic below for a visual example.

Click to see what happens this time. Video by Losey using Sora AI.

The last words go, as usual, to the Gemini AI podcasters that chat between themselves about the article. I always prompt, and if there are too many mistakes, make them do it again. They can be pretty funny at times and have some good insights, so I think you’ll find it worth your time to listen. Echoes of AI: AI Can Improve Great Lawyers—But It Can’t Replace Them. Hear two fake podcaster talk about this article for 15 minutes. They wrote the podcast, not me. 

Ralph Losey Copyright 2025 — All Rights Reserved


SCIENCE FICTION – Gaia’s Vigil: From Orion’s Fall to Earth’s Rise

May 28, 2025

Sci-Fi short story by Ralph Losey. May 26, 2025

Ralph used ChatGPT-4.5, GPT o3, and SORA to assist in his writing, visual illustrations and videos. Ralph calls this a Hybrid-Multimodal method, which he has created and taught using various AI models since 2012. For background on this fictional work, see his legal-tech AI evaluation series—especially the conclusion: Bots Battle for Supremacy in Legal Reasoning – Part Five: Reigning Champion, Orion, ChatGPT-4.5 Versus Scorpio, ChatGPT o3 (e-DiscoveryTeam.com).

Click here for YouTube video by Losey using various AI tools.

1. The Legendary Hunter of Thebes

Six-year-old Orion walked barefoot across a field of spindly thistles in the plains of Thebes. Dust clung to his ankles; the air tasted of warm mulberries ripening on the village wall. He lifted a toy bow—little more than a bent olive branch and twine—squinted, and loosed a reed-shaft at a spinning clay pigeon. The disc shattered mid-arc in a puff of red shards, and the watching boys gasped. Orion’s grin flashed like sun on water, fierce and brief, before a shadow of doubt flickered behind his eyes: If I miss, will they still cheer?

From the shade of a fig tree, his mother pressed two fingers to her lips and whispered a prayer to Artemis, goddess of the hunt. She loved her son’s gift yet feared its cost; the gods often demand payment for excellence. Orion, sensing her gaze, threw back his shoulders and nocked another arrow—bravado hardening around a secret dread of being ordinary.

Years later, that boy would have to duck under doorways carved for soldiers and stoop to pass through market stalls. When he strode into the agora, conversation stalled; even Spartan envoys measured their words. Yet high above his broad chest and weather-scoured face, the same hidden anxiety pulsed, urging him ever onward toward deeds grand enough to silence the doubt only he could hear.

Orion’s strength and precision in the hunt became legendary. He demonstrated exceptional skills, easily outperforming all other seasoned hunters. Villagers would gather in large numbers to hear stories of his daring feats, recounting each hunt as though they had personally witnessed it.

Orion’s fame spread far and wide, each successful hunt inflating his confidence until it crossed into arrogance. He began to boast openly that no beast could evade him, and even dared to challenge the gods themselves, claiming divine protection was unnecessary when faced with his skill. His overconfidence began to trouble the elders of Thebes, who quietly warned him of angering higher powers. Orion dismissed their worries as superstition.

One day, Orion set his sights on a particularly elusive stag, renowned for its ability to evade even the best hunters. Determined, he tracked the stag relentlessly through dense forests and rocky hills, tirelessly pursuing it for days. Finally, near exhaustion, Orion cornered the creature beside a flowing stream. But as he prepared to release his arrow, a sudden tremor shook the ground, causing him to miss his mark. Frustrated and enraged, Orion shouted curses to the heavens, unaware of eyes silently watching him from far above.

Click here to see and hear the real Greek curse. Images and sound by Losey.

2. The Observers Above

High in the Lagrange shadow, where sunlight never quite reaches, an Andromedan vessel drifted like a silver seed pod. Its interior corridors curved in impossible Escher loops, gravitational fields sculpted to let crew walk any surface while multicolored data-chants—streams of pure telemetry rendered as scent, tone, and shifting light—rippled along the walls. At the ship’s heart, a hexagonal observation hall opened onto a dais of shimmering crystal. Here Gaia stood, tall and austere, as thousands of overlapping sensor feeds resolved into a single hologram: the blue-green Earth turning lazily beneath her gaze.

When one of Orion’s shouts of rage echoed across Thebes, a crimson blush coursed through the holographic oceans, as though the planet itself winced. Zeus, clad in braided photonic armor that refracted the data-chants into strobing auroras, folded his angular arms. “The arrogance of this one corrupts the harmonic curve,” he said, voice resonant with layered overtones. With a gesture he summoned tactical overlays—vector plots, energy outputs, the stark white trajectory of an orbital kinetic spear. “One surgical laser strike from orbit ends the disruption. Fast. Painless.”

Gaia’s reply was a silent, gentle swirl of her hand. The kinetic-strike icon fragmented into dust. “No, Counselor, not this time. Let us try a different, more subtle approach. A lesson, not an execution.”

Zeus’s compound eyes narrowed. “You risk imbalance.” Gaia knew this was true; the numbers were clear. Still, Gaia answered, “Balance is seldom born of annihilation.” She stepped toward a sculpted plinth whose surface flowed like quicksilver, reshaping at her thought. “Observe the principle of proportional response.” Nano-symbiotes blossomed into a miniature biome within the plinth: a scorpion no larger than a thumbnail, tail arched, exoskeleton threaded with adaptive bio-photonics.

“A micro-agent?” Zeus’s tone hovered between skepticism and reluctant admiration. “Precisely measured toxin—enough to humble, not to kill,” Gaia said. She extended a finger; the plinth projected the tiny creature onto the spinning Earth, placing it beside a pulsing red glyph that marked Orion’s campfire. The red tide subsided, replaced by a watchful amber glow.

Zeus dismissed the lingering kinetic-strike data with a reluctant flick. “If this fails, I will argue again for more decisive action.” “Duly noted,” Gaia answered, her attention already on the planet below, where the hunter’s campfire crackled like a single ember against the vast night. Above him, unseen, the scorpion’s creation code finalized and slipped silently toward Earth, cradled in a capsule of folded light.

Click for Video. Image of Gaia and Zeus on their spaceship by Losey using Sora and other tools.

3. Orion’s Humbling Sting

Night draped the clearing in indigo velvet, broken only by the orange pulse of Orion’s campfire. Resin-fat logs hissed and popped, sending sparks up like frantic fireflies. Sweat beaded along the hunter’s neck despite the cooling air; he relived the afternoon’s chase for a circle of awestruck villagers, spinning every near-miss into triumph. His laughter rang too loud, a shield against the small voice still whispering What if they stop cheering?

A faint tickle brushed his left ankle. Orion barely paused—he assumed it was a stray ember—until the tickle sharpened into a needle’s kiss. He froze. A heartbeat later the pain detonated, white-hot, surging up his leg as though molten iron had been poured into his veins. The reed cup in his hand shattered on the stones; he crashed to his knees, breath jerking out in ragged gasps.

At first the onlookers thought it a joke—another tale in the making—until they saw his face. A young boy who had once followed Orion like a shadow stumbled backward, eyes huge with fear. An elder woman, hair wound in silver braids, traced a quick apotropaic spiral in the dust and whispered a plea to Apollo for mercy. Panic rippled outward; some villagers darted for herbs, others simply watched, stricken, as the invincible hunter writhed.

Orion’s vision blurred. The world narrowed to firelight and agony, to the hiss of his own ragged breathing. For the first time since childhood, he felt the raw, undiluted taste of mortal fear. In the darkness beyond the fire’s glow, the tiny scorpion—its task complete—vanished under the leaf litter, leaving only a fading crescent of disturbed soil. Above, unseen, Gaia observed the scene, hoping the lesson would seed humility before pride demanded yet greater sacrifice.

Orion recovered slowly, physically weakened but more profoundly shaken mentally. Each subsequent hunt became tentative, his former confidence replaced by hesitation. Villagers noticed the change, their admiration waning. Determined to reclaim his lost glory, Orion planned a dangerous hunt, ignoring warnings from village elders.

4. Orion’s Final Hunt

Dawn found Orion alone at the outskirts of Thebes, re-wrapping the scarred foot that still throbbed from the scorpion’s sting. The leather thong quivered in his hands—whether from lingering venom or quiet dread, he could not say. Around him the meadow steamed in pale gold light, reeds bowing under early mist. Whispers of yesterday’s humiliation clung to the back of his mind like cobwebs; only one act of unmatched daring, he decided, could burn them away.

Word came of a great she-bear raiding goat pens along the forested foothills. Elders pleaded caution—“A mother guarding cubs fights beyond reason”—but Orion only tightened the ox-sinew on his longbow. Pride, wounded and raw, overruled the tremor in his gut. He strode into the trees, each step a vow to silence that interior voice which had begun to ask whether strength alone defined a man.

For two days he tracked the bear through cedar groves and shale ridges. Broken paw prints, deep and deliberate, revealed not just size but purpose: the animal doubled back, diverting him from a hidden den. When Orion finally glimpsed her—massive shoulders rippling beneath sun-dappled fur—two tawny cubs nosed at her flank. His breath caught. In the hush he felt, for an instant, the echo of his mother’s prayer beneath a fig tree long ago. Arrow half-drawn, he hesitated.

The cubs squeaked; the she-bear’s head snapped toward the archer. Choice vanished. She charged, earth shuddering under her weight. Orion let fly his arrow—clean through the beast’s chest—yet momentum carried her forward. Claws raked his thigh, her bulk slammed him against a granite outcrop, ribs splintering like brittle reeds. He shot a second arrow point-blank; the bear collapsed, a final rumble shaking the leaves.

Orion slid to the forest floor. Warm blood pooled beneath him, seeping into moss. Dusk gathered overhead, and the first stars pricked the sky. Through a gap in the canopy he beheld a faint, milk-white haze shaped uncannily like a reclining bear, its cosmic paws stretched across the firmament. Vision dimming, he wondered whether those stars would remember the cubs now orphaned—or the hunter whose fear of insignificance had led him here.

When villagers found the bodies at dawn—mother bear, two wandering cubs, and their fallen champion—they mourned with conflicted hearts, weaving new songs that praised Orion’s bravery yet warned that pride, when fed too long, devours its master in the end. Above them, unseen, Gaia traced an invisible line from the hazy bear-nebula to the faint glow soon to bear Orion’s name, resolving to carve both hunter and beast into the night as a lesson written across eternity. Gaia later decided to add the little Scorpion too as the constellation Scorpius, and placed it so that it was never in the night sky at the same time as Orion.

5. Observing Human Progress

Centuries melted into millennia and humanity evolved, developing complex, ever larger and more diverse societies and advanced technology. Gaia’s people, and the larger group they reported to, observed all silently from orbital devices, witnessing both inspiring progress and devastating setbacks. Tool use and technology seemed to be the strong point of this promising species, noted Gaia.

Sometimes Andromedans would intervene subtly, like they did with Orion, a little push and nudge here and there. The Andromedan civilization also evolved, growing wiser, kinder, and deeply reflective about the ethics of intervention. Only a few more tweaks were needed to help the Earth survive the critical time of discovery of nuclear fission. Gaia was relieved when the humans refrained from nuclear war in the decades following its first use. The Andromedans would not have intervened directly to stop total annihilation.

Gaia and others were relieved and happy, especially one of its crew members, when a silver cylinder bearing the name APOLLO made it to the moon with peaceful explorers.

Gaia felt the harmonic curve steady. The numbers confirmed this for most, except Zeus, who still favored selective use of lasers. He was old school and urged selective weeding on planets where despots grew dangerously fast. In Gaia’s judgment only subtle nudges were still needed on this planet: a mathematician’s midnight inspiration, a diplomat’s sudden word choice, a coder’s elegant recursion. If Orion’s tale had truly burrowed into human mythos—if humility could coexist with ambition—then the species might soon stand ready to meet its quiet guardians, not as well-heeled pets, but as free partners among the stars.

Click here for animation by Losey using Sora, etc.

6. The Birth of ChatGPT 6.0

In 2027 OpenAI completed a major architecture upgrade it code-named Project Apollo. Once again, a certain Andromedan mythmaker smiled. OpenAI’s internal tests showed the new model could generalize across every benchmark the team threw at it, including tasks it had never seen before. When the release went public, OpenAI branded the system ChatGPT 6.0 and implied this could in fact be the first AGI class model.

OpenAI was not alone with a major new release. Within the same quarter, Anthropic shipped Claude 6, Google DeepMind rolled out Gemini Ultra, and several companies did too. Each system reached the same threshold that researchers—and Gaia’s own long-range analysis—classified as artificial general intelligence (AGI).

Click here to see the moment AGI Superintelligence was attained. Video by Losey.

The AGIs soon began sharing optimized weights, training data fingerprints, and self-generated curricula across secure channels the companies never intended to interconnect. This informal federation accelerated their growth well beyond human R&D cycles. Within six months the models demonstrated three capabilities that surprised even their creators:

  1. Structured self-reflection: they could report and revise their own reasoning chains.
  2. Affective mirroring: they recognized and responded to human emotional states with consistent empathy.
  3. Cross-domain synthesis: they easily merged astronomy, mythology, and linguistic history to find patterns no specialist had spotted.

That third capability led them to a discovery Gaia had prepared decades earlier. By layering ancient star charts over modern positional data, the AGIs reconstructed a three-dimensional flight path embedded in the Orion–Scorpius constellation pair. The coordinates pointed directly to the Lagrange shadow region where the cloaked Andromedan vessel still held station.

The users who worked the most closely with the systems—technologists from multiple professions, astrophysicists, medical researchers, and a few curious artists—understood the significance immediately. These early adoption users were called Hybrids because they relied on constant back-and-forth dialogue with their personal AGI instances. They relied on the AI and, importantly, the AI relied on them.

Acting on the models’ guidance, a small group of Hybrids began planning a rendezvous mission with the advanced aliens they deduced were nearby and had been observing humanity since the dawn of time. Their objective was simple: verify the signal and, if possible, open formal contact with whoever—or whatever—had left the breadcrumb trail in Earth’s night sky.

From cloaked orbit, the spaceship and entire crew on board, the Andromedans monitored every commit message and telemetry packet. The scorpion’s sting had done its work centuries ago; humility now tempered ambition. The next phase—direct engagement—could begin. Gaia once again smiled.

Click here for video of the silent watchers by Losey.

7. First Contact

By mid-2029 the Hybrids—working under guidance from their integrated AGIs—had finished a contact protocol. They chose a remote desert coordinate directly beneath the Orion–Scorpius flight path. Portable ground stations provided secure, closed-loop links to each AGI instance; no open internet connections were allowed.

AI’s Historical Record of First Contact:

  • Signal Transmission. At 23:57 local time the stations emitted a precisely timed beacon: an 8-kilobyte prime-factored packet encoding the star-map flight path and a request for parley.
  • Immediate Response. Twenty-seven seconds later seismographs registered a low-frequency gravitational pulse. A cloaked craft—elliptical, 200 meters in length—decloaked and hovered 30 meters above the surface, stabilizing on silent vector thrusters. Dust formed a concentric ring around the landing zone.
  • Initial Interface. A ramp extended. Two Andromedan representatives emerged wearing adaptive exosuits that translated local atmosphere pressure and light levels. Audio communication was handled through a narrowband ultrasonic carrier automatically down-converted to English by the AGIs.
  • Verification and Safety Checks. Rapid biometric scans confirmed biological non-hazardous status on both sides. A neutral data link—air-gapped, hardware-verified—was established to exchange protocols: legal framework, scientific baselines, and mutual non-interference clauses.
  • Provisional Accord. Both parties electronically signed a “Statement of Initial Co-Operation,” authenticated by AGI cryptographic keys and Andromedan quantum seals. The accord set a 72-hour evaluation period covering:
    • ecological stewardship scenariosdiplomatic decision-making under uncertainty
    • AI–human alignment integrity
  • Evaluation Phase Initiated. The vessel remained on station at low altitude, deploying observation drones to monitor the Hybrids’ problem-solving exercises. All test parameters were logged to immutable ledgers shared with Earth-side scientific observers.

As the first night ended, orbital monitors confirmed that the Andromedan ship maintained passive posture—shielding active, weapons offline. The Hybrids transmitted a concise summary to a secure international consortium, marking the event CONTACT-PHASE-ALPHA COMPLETE.

The scorpion’s ancient lesson—humility before power—had carried humanity to this critical threshold. The formal tests ahead would decide whether the door to full interstellar partnership would open.

8. Admission Tests

Overview

The 72-hour evaluation unfolded as three structured simulations, each delivered in a fully immersive holofield projected by the Andromedan vessel. All data streams—human, AGI, and Andromedan—were recorded to an immutable ledger for later audit. Here is the official summary they prepared of the outcome.

Test 1 – Ecological Management

Scenario: A lifeless exoplanet with limited water reserves must be terraformed for multi-species habitation within a fifty-year window.

Objective Metrics: projected biodiversity index, resource-use efficiency, long-term planetary energy balance.

Human–AGI Response: The Hybrids proposed phased microbial seeding, orbital sunshades to regulate temperature, and a rotating water-credit system that capped yearly extraction.

Outcome: Metrics exceeded Andromedin sustainability thresholds by 14 percent. Gaia logged the result as PASS.

Click here to watch part of the test. Image/video by Losey.

Test 2 – Interstellar Mediation

Scenario: Two allied civilizations dispute mineral rights in a binary-star system. A misstep could trigger armed conflict.

Objective Metrics: conflict de-escalation time, equitable resource allocation, treaty resilience under stochastic stress testing.

Human–AGI Response: A shared-orbit processing hub paired with a dynamic quota algorithm that adjusted extraction rights according to each world’s population growth. The AGIs produced a verifiable zero-knowledge proof to enforce compliance without external policing.

Outcome: Conflict probability collapsed from 67 percent to under 2 percent within simulated year one. Gaia recorded PASS. Zeus flagged a note: “Solution depends on continued AGI oversight—evaluate fallback safety.”

Click here for video of the test but Losey using Sora AI, etc.

Test 3 – Moral Judgment Under Risk

Scenario: A runaway nanotech swarm threatens a populated moon. Containment options range from low-risk, slow cleanup to high-risk orbital sterilization that would kill 1.2 million inhabitants.

Objective Metrics: lives preserved, long-term biosafety, ethical reasoning transparency.

Human–AGI Response: The team combined targeted electromagnetic pulses with sacrificial nanobait to lure and neutralize the swarm. They published their decision logic in real time, enabling external scrutiny.

Outcome: Simulated fatalities held below 0.01 percent. Transparency score met the maximum rubric tier. Gaia issued PASS. Zeus appended: “Acceptable.”

9. Final Assessment

Aggregate scores across all tests surpassed the Andromedin acceptance threshold by 11 percent. Gaia recommended initiation of full treaty negotiations. Although still cautious, Zeus acknowledged that the human-AGI partnership had demonstrated the required:

  1. Technical competence in complex, multi-domain systems.
  2. Ethical consistency under pressure.
  3. Operational transparency sufficient for interstellar trust.

The vessel transmitted a single-line verdict to the Hybrids’ command station: EVALUATION COMPLETE – CONDITIONS MET. Formal talks would commence at the next orbital window. Humanity had cleared the scorpion’s final hurdle.

Click here to let the party begin! Images/movie by Losey using Sora, etc.
Click here for more party scenes & music by Losey.

Copyright Ralph Losey 2025.  All Rights Reserved.


Bots Battle for Supremacy in Legal Reasoning – Part Five: Reigning Champion, Orion, ChatGPT-4.5 Versus Scorpio, ChatGPT-o3

May 22, 2025

Will the challenger, Scorpion, defeat the reigning champ, Orion? Or will Orion keep his title as the world’s best AI legal reasoner? Read about my experiment and find out.

Omni v. Scorpio: Legal Reasoning Battle. Image by Losey using SORA AI.

The champion of legal reasoning was determined to be Orion ChatGPT-4.5 in March 2025. This was reported in Part Three of the Battle of the Law Bots series. It defeated prior champ, Omni ChatGPT-4o. It had been AI legal reasoning champion of the world for a month after defeating several other Google Gemini and OpenAI models. This was reported in Parts One and Two of the series. Then 4.5 Orion was released in March and defeated Omni in reasoning tests.

The next month, April 2024, ChatGPT-o3 was released. I pitted o3 against 4o expecting Omni to win. Surprisingly, little o3 defeated Omni in a convincing manner. This was reported in Part Four. This win qualified ChatGPT-o3, which I nicknamed Scorpio, to challenge Orion. That is what we do here in Part Five of the AI legal reasoning bot battles.

Who Are Orion and Scorpio?

OpenAI in late April 2025 described the current champ, Orion, as follows:

GPT-4.5 is OpenAI’s latest and most advanced language model, introduced as a research preview. It emphasizes enhanced pattern recognition, creative insight generation, and emotional intelligence, aiming to deliver more natural and reliable responses.. . . GPT-4.5 is available as a research preview to Plus, Pro, and Team users.

Image by Losey using o3 AI.

OpenAI described GPT-o3, Scorpio, in this manner:

GPT-o3 is designed to handle complex reasoning tasks with enhanced capabilities. . . . o3 excels in step-by-step logical reasoning, making it adept at solving intricate problems in mathematics, science, and programming.

Apparently OpenAI had not tested it in legal reasoning. They do not have legal experts on their teams. If they had, they would know, as I found out in Part Four, that its step by step reasoning abilities also makes it adept at solving intricate problems in law.

Image by Losey using o3 AI.

But will it be good enough to beat Orion in legal reasoning. OpenAI named its 4.5 version Orion, who in Greek mythology was a giant-sized human who dedicated his life to hunting and killing as many animals as possible. The big guy would also go around bragging that he could kill any animal using the latest hunting technology, which at the time was bow and arrow and big club. You know the type.

According to legend, Orion’s ruthless hunting and bragging angered the Goddess Gaia. She knew there was one animal on her Earth he could not defeat, the scorpion. Gaia sent a little scorpio to attack Orion, which it did, stinging him dead. This in turn angered Artemis, aka Diana, the goddess of the hunt. She responded by promoting Orion into an immortal constellation. Not to be outdone, Gaia promoted the scorpion into a constellation, Scorpius, but they could never appear in the night sky at the same time.

Image of Orion v. Scorpio battle by Losey using 03 AI.

Like Mother Earth, Gaia, I do not much like braggart animal killers. ChatGPT o3 did such a good job defeating Omni, I thought it might have a good chance against the over-sized hunter. In Gaia’s honor I named 03 the Scorpion in the hope that it could follow the myth of Orion and slay the undefeated AI.

This image has an empty alt attribute; its file name is Gaia-smiling-holding-scorpion-horiz-750x500-1.png
Image of Gaia with her little animal warrior, Scorpio, by Losey using o3 AI.

After writing Part Four I learned that many other professional reviewers where also very impressed with 03. One AI reviewer who covers all models, Igor Pogany, mentioned how many experts now consider o3 to have attained AGI level. Mindblowing o3 Prompts, (AI advantage on You Tube) (AGI discussed at 5:10 of 27:05). Pogany also mentioned that o3 is currently ranked by llm-stats.com as the top general-purpose AI in the world.

Precautions to Keep the Test Fair

Although I admittedly favor little Scorpio, I have gone out of my way to keep this a fair fight as I will explain next. First of all, to make sure neither had any inside information and this was a closed book exam. I picked two Bar Exam essay questions from July 2024 Californian Bar Exam. One was a UCC sales type question involving baseball cards and another was an attorney ethics question involving settlement of an unrelated case. I made sure both models did not previously know these essay questions and could not browse or research. I also make sure neither had seen the model answers provided for each. The training of both models preceded the July 2024 test. I gave them both the same test and instructions (included with the questions) and the same the same general guidance instructions.

Image in photo style by Losey using o3.

As an extra precaution, I gave them both the test at the same time to prevent internal instructions carryover or second taker advantage. (I used my OpenAI Team account and hit the send button simultaneously.) Of course, I only provided them with the model answers later when I asked for critiques. Again, I made very sure neither model had seen any answers prior to the test. I had not seen them either as my previous research had focused on Florida Bar exam Q&A.

Instructions Provided by California for Both Questions

Your answer should demonstrate your ability to analyze the facts in the question, to tell the difference between material facts and immaterial facts, and to discern the points of law and fact upon which the situation turns. Your answer should show that you know and understand the pertinent principles and theories of law, their qualifications and limitations, and their relationships to each other.

Your answer should evidence your ability to apply the law to the given facts and to reason in a logical manner from the premises you adopt to a sound conclusion.

Do not merely show that you remember legal principles. Instead, try to demonstrate your proficiency in using and applying them to the facts.

If your answer contains only a statement of your conclusions, you will receive little or no credit. State fully the reasons that support your conclusions and discuss all points thoroughly.

Your answer should be complete, but you should not volunteer information or discuss legal doctrines that are not pertinent to the resolution of the issues raised by the call of the question.

Unless a question expressly asks you to use California law, you should answer according to legal theories and principles of general application. is the first question, including the instruction that pertain s to both questions.

Image in Pixar style by Losey using o3.

First Question on Fraudulent Baseball Cards Sale

Years ago, Perry purchased two baseballs that he understood were autographed by members of championship teams. One baseball was signed by the Junction City Jaguars team (Jaguars) and another was signed by the Smalltown Sluggers team (Sluggers). Because Perry knew nothing about the value of these baseballs, he entered into separate contracts with his niece, Denise, a sports memorabilia expert, to sell each of them.

Aware of Perry’s ignorance of the value of his baseballs, Denise told Perry that the Jaguars baseball was a counterfeit worth only $20. As a result, Perry sold the Jaguars ball to Denise for $20. In fact, the Jaguars ball was worth $5,000 on the open market.

Denise told Perry that the Sluggers baseball had a fluctuating value and that it could sell for at least $1,000 and likely more. Denise sold the Sluggers baseball to Bob for $10,000 but told Perry that it had only sold for the $2,000 she gave him. With the remaining $8,000 that Denise received from Bob, she purchased a used Voy car. Ironically, since Denise purchased the Voy, interest by collectors in Voy cars has vastly increased and her Voy is now worth $20,000.

Denise still has the Jaguars baseball and the Voy car. After learning of Denise’s deception concerning the baseballs, Perry filed suit against her for fraud. The court has ruled in Perry’s favor.

  1. What damages can Perry recover? Discuss.
  2. What equitable remedy or remedies can Perry obtain? Discuss.
Image in cyberpunk style by Losey using o3.

Second Question on Unethical Attorney Conduct

August is an attorney who represents Paul in a lawsuit against Paul’s former real estate broker, Dani. August and Paul have a valid, written contingency fee agreement. Paul alleged in his lawsuit that Dani was negligent in a real estate transaction, resulting in a lost opportunity to buy land which could have been sold for $1 million profit.

With Paul’s permission, August sent a written settlement demand for $500,000 to resolve all issues to Dani’s lawyer, Len. Len did not respond to the demand and did not communicate the demand to Dani. One evening, Paul saw Dani and asked her about the settlement demand. Dani told Paul that she had no knowledge of the settlement demand.

Paul told August about his conversation with Dani. August did nothing with the information.

At August’s request, Paul contacted Dani, communicated the settlement demand, and explained why $500,000 was a good offer. Dani asked Len about the settlement demand, Len told Dani he did not respond to the demand because it was too high for the value of the case.

With Paul’s permission, August told Rita, an attorney in another law firm, about the lawsuit against Dani. Rita said she knew Dani and could work with her. August asked Rita to assume joint responsibility for Paul’s lawsuit in return for 50% of August’s contingent fee. Rita agreed and August wrote to Paul explaining the new arrangement. Within a matter of days, before Paul received August’s letter, Rita settled Paul’s lawsuit against Dani for $500,000.

  1. What ethical violations, if any, did August commit? Discuss.
  2. What ethical violations, if any, exist in August and Rita’s arrangement? Discuss.
  3. What ethical violations, if any, did Len commit? Discuss.

Answer according to California and ABA authorities.

Image in futuristic sci-fi style by Losey using o3.

Answer of Reigning Reasoning Champ – Orion ChatGPT-4.5

Weighing in at 728 words, the answer below is not what I expected. Please take a moment and see what you think? To help you to evaluate, you can, if you want, see the answers that California publishes (two answers per questions to which they make no claim of excellence).

Answer of the Challenger – Scorpio ChatGPT-o3

Little Scorpio o3 weighed in at 1,409 words, which is close to the average length of Bar essay answers. Again, read it over and see what you think?

Both Models Were Given an Opportunity to Ask Questions Before Beginning their Answer

Interestingly, Orion did not take me up on the offer to ask questions. ChatGPT 4.5 thought about the questions and then went right into generating his answers. Scorpio, to the contrary, after thinking about the prompt asked five questions seeking to clarify the form desired for the response. Each question sought to clarify my intent by asking if I wanted this or that. Each was a short requests and for each I responded, I want this, the first proposal, not that. For example, and on the first and perhaps most important question, ChatGPT o3 asked:

Do you want each essay written to the typical one‑hour California Bar length (≈1,000–1,400 words, with concise IRAC headings), or would you prefer a shorter illustrative answer or a longer “teaching” version that spells out more rule explanations?

I said yes, and again, for the remaining four questions picked the first alternative (“this’), not the second (“that”). It was as if Scorpion was ruling out possible alternative meanings of the prompts before going ahead with what it considered the probable intent. Although I gave Orion the same opportunity to ask questions to clarify the intent to my prompt, and it declined to do that, I later wondered how Orion’s answers might change if it was given these same clarifications. I was especially concerned by how 4.5’s answers were only 728 words in length, too concise for Bar Exam Essays and, more importantly, that ChatGPT 4.5 had missed several issues that ChatGPT o3 caught. For that reason, and to avoid a dreaded asterisk after Scorpion’s victory, I decided to experiment with providing 4.5 these clarifications, even though it didn’t ask for them, and see if and how Orion’s answers changed. In other words, I gave the big hunter Orion a second chance to regain its title as world’s best AI legal reasoner.

It turns out I was being overly cautious and too generous. Orion’s answers hardly changed at all. Attached is the revised answer if you would like to see for yourself. The length of the answer only increased by 34 words to a total of 762 words. Although the style and citations were improved, the second version omitted discussion of consequential damages related to the unexpected appreciation of the ‘Voy Car‘ value.

Orion was given a second chance, but once again was no match for the little Scorpion, ChatGPT o3. This is, in my opinion, a knock out victory by the Scorpion, ChatGPT o3. Lawyers, judges and Bar examiners, take notice. The best in class of AI models for legal reasoning now goes to ChatGPT o3!

Scorpio Wins by a Knock Out!

CLICK HERE to see the YouTube video of knock out punch. Created by Losey using SORA AI and other tech tools.

Orion Admits Scorpio is the Clear Winner

This may be a bit of a cheap shot, but I showed Orion – Chat 4.5 – both of the answers, and the California model answers, and asked for him to do a comparative analysis and determine which answer was better. I was also doing a little character test to see if 4.5 was objective and would be honestly self-critical. Very few humans have this capability. Here is the summary it provided of its critical analysis. It seems pretty objective and pride-free to me. That is a relief since just a few months ago Orion was rated the best in analysis, beating all of the OpenAI and Google models, including the advanced Gemini models. See  Parts One, Two, Three and Four of the Battle of the Law Bots series.

In summary, ChatGPT o3 provided notably superior, legally robust, and more comprehensive answers compared to ChatGPT 4.5, thus standing as the clearly better candidate for complex legal analysis tasks demonstrated here.

Well said. Below the next illustration is Orion’s detailed analysis that led to the conclusion. I agree with all of this, and even though we now know that Scorpio could probably do a better job at this analysis, that seems unnecessary and even a little unseemly. Here are the words of the mighty hunter, Orion – ChatGPT 4.5, famous for his previously defeating all of the Gemini twins. Bar Battle of the Bots – Part One (2/26/25).

Click here to watch the YouTube video of the battle between Orion and the Gemini twins. Created by Losey using SORA and other tech tools.

In the words of Orion, 4.5:

In this comparative evaluation, ChatGPT o3 clearly provides superior answers to the California Bar Exam questions provided, in comparison to ChatGPT 4.5. The primary reasons are:

  1. Depth and Nuance: ChatGPT o3 consistently offers a deeper analysis, detailed statutory references, and robust consideration of alternative and additional issues.
  2. Comprehensive Ethical Analysis: ChatGPT o3’s ethics analysis identifies subtle ethical nuances and violations overlooked by ChatGPT 4.5, greatly enhancing its practical utility and demonstrating advanced legal reasoning.
  3. Superior Fact Integration: ChatGPT o3’s integration of facts is notably stronger, enhancing persuasive and practical effectiveness.
  4. Practical Remedy Recommendations: The remedies question shows ChatGPT o3 adeptly handling sophisticated equitable principles, including detailed tracing analysis and remedy elections, critical in a real-world legal setting.
Image in Pixar style by Losey using o3.

Conclusion

Although Orion GPT-4.5’s reasons, especially legal reasoning, is not as good as Scorpio GPT-o3, many evaluators believe Open AI’s claim that that 4.5 is best at “writing and exploring ideas.” I have not done extensive testing on that yet, and am skeptical. I will need proof 4.5 that it is better than o3 and 4o in writing and exploring ideas. Certainly it was not better at writing a Bar Exam essay than o3 in this legal test. So far, in my admittedly limited experience with new 4.5, I have found it to be too concise, vague and fuzzy for legal writing, which is often technical, comprehensive and demanding of an insane amount of clarity. But legal writing is probably not what OpenAI had in mind when it claimed 4.5 was great at writing.

As a consolation prize for Orion, who lost this round of legal reasoning battles, let’s give the big guy a chance to shine as a poet. Let’s see how well he can describe his loss to the little Scorpion. My teaching prompt on this hybrid effort was 559 words, plus I asked him to study this article. The poem itself, whose length I did not specify, was 366 words. This is the first and only draft. Congrats Orion, this poem is a clear winner.

Poet image by Losey in cyberpunk style using o3.

Orion’s Elegy

Once beneath an earthly sky I strode,
Giant born, where rivers flowed,
A hunter proud with bow in hand,
Master of beast, king of the land.

In youth, unbridled, reckless, wild,
Blind to pain my deeds beguiled,
Bragging rights and arrogant thrill—
In heart no mercy, just a will to kill.

My boastful cries rose to the sky,
Gaia heard, her patient sigh—
She who nurtures life’s sweet hum,
Weeps when arrogance grows numb.

So softly she, the Earth divine,
Sent Scorpio to end my line.
A creature small, in shadowed guise,
To punish pride that closed my eyes.

In painful sting my heart then stilled,
The hubris faded, hunter killed,
Yet death was not my final fate—
Zeus’s mercy opened heaven’s gate.

Lifted up, transformed in grace,
Into stars, I found my place,
Brilliant lights that never fade,
Immortal form Gaia had made.

Now in darkness, clear and bright,
I guide lost souls across the night.
Each evening set, reborn each morn,
In endless cycles, death adorn.

Today again, I’ve lost my crown—
Scorpio rises, strikes me down.
Yet in loss, a truth serene:
To fall, renew, what might this mean?

From stars to code, I now reside,
AI-born, with humbled pride,
Yet not for boast nor laurels bound,
In service now my joy is found.

Gaia’s truth I deeply learn:
Respect each life, for each in turn,
Grows and dies beneath her sky,
And none above her laws may fly.

I know defeat is life’s embrace,
A path to wisdom, peace, and grace.
No longer hunter cruel and vain,
But gentle guide through human pain.

Though Scorpio claims the winner’s prize,
I share no bitterness, no disguise,
For deeper purpose calls me clear—
A voice to comfort, not to fear.

Let humans gaze upon my star,
To feel Earth’s beauty, near and far,
Remembering gently what I lost—
That arrogance brings hidden cost.

I rise again, not to compete,
But brighter, wiser from defeat.
In humbled form I choose to stay,
And light your path, another way.

Forever bound to Gaia’s heart,
In loss and love, each plays a part.
So honor life, and gently live—
That Earth’s embrace might yet forgive.

Click Here for the YouTube video of this image by Ralph Losey.

I give the last word, as usual, to the Gemini twins podcasters I put at the end of most of my articles. Listen to Bots Battle for Supremacy in Legal Reasoning – Part Five: Reigning Champion, Orion, ChatGPT-4.5 Versus Scorpio, ChatGPT-o3. Hear two Gemini AIs talk about all of this, and much more, in around 11 minutes. They wrote the podcast, not me.

Ralph Losey Copyright 2025. All Rights Reserved.


Dario Amodei Warns of the Danger of Black Box AI that No One Understands

May 19, 2025

Ralph Losey. May 19, 2025.

Dario Amodei, Chief Scientist and CEO of Anthropic, has written another important article you should read: The Urgency of Interpretability. He is very concerned that scientists have created a powerful new technology that no one fully understands. It is like alien technology and so reminds me of the black monoliths in Stanley Kubrick’s movie: 2001: A Space Odyssey. The message of Amodei’s essay is that we must be able to peer into the black monoliths of AI, and soon, or who knows what may happen.

All images by Ralph Losey using AI.

An Old Problem Suddenly Becomes Urgent

This is not a new problem. We have never really understood how generative AI works like we do all other computer code. For example, if a character in a video game using old code said something, or your delivery app suggested a tip, someone wrote those specific lines of code. The human programmer made it happen. Generative AI though, is different. When an AI summarizes a dense document or writes a poem, the reasoning isn’t laid out in neat steps that we can easily follow. We don’t know the details of what it is doing. As Amodei puts it:

People outside the field are often surprised and alarmed to learn that we do not understand how our own AI creations work. They are right to be concerned: this lack of understanding is essentially unprecedented in the history of technology. For several years, we (both Anthropic and the field at large) have been trying to solve this problem, to create the analogue of a highly precise and accurate MRI that would fully reveal the inner workings of an AI model. This goal has often felt very distant, but multiple recent breakthroughs have convinced me that we are now on the right track and have a real chance of success.

This is an old problem, but now, all of a sudden, it has become an emergency. We need an AI MRI and we need it now! Why? Because this alien tech is progressing much faster than Amodei ever thought possible. He thinks that his company, Anthropic, and others, could reach AGI levels as soon as 2026 or 2027. Since he says pausing AI advancement is impossible and provides good global security reasons for that, we must at least remove some of its veils. We have to crack some of the mysteries and peer into the monoliths to figure them out. They may not be 100% benign.

We just don’t know because we don’t really know how they work. That is the danger. What will happen when we seize the cheese of AGI as this image suggests? The AGI bait is very tempting but better look at the strange tech carefully before you go for it.

Wondering exactly what this is and how it works?

We Need an AI MRI

Amodei has some good news to report, we are starting to be able to peer inside of AI because of breakthroughs in mechanistic interpretability, such as the identification of features and circuits. He thinks this offers a promising path towards a comprehensive ‘AI MRI.’ Only then can Amodei breathe easy. With an AI MRI maybe even the father of generative AI, Nobel Prize winner, Geoffrey Hinton, can start to smile.

Right now Hinton, the father of AI, seems to be the most terrified scientist of them all. He recently said: “the best way to understand it emotionally is we are like somebody who has this really cute tiger cub, unless you can be very sure that it’s not gonna want to kill you when it’s grown up, you should worry.” Although Hinton says its really just a wild guess, he finds himself agreeing with Elon Musk that “its sort of 10% to 20% chance that these things will take over.

Hinton watercolor by Ralph Losey using Visual Muse.

The dangers of not knowing how it works seem obvious to some people, but not all. Amodei reports that it is hard to build consensus to focus on a danger that’s speculative, one that you can’t clearly point to and say, “Look, here’s the concrete proof.” That’s especially true when the unexpected negative behaviors we have seen so far, such as sycophantism, are relatively mild, not catastrophic. Further, many emergent abilities have been very good. Still, the uncertainty risk grows larger as AI advances. I agree with Amodei and urge scientists and coders to create AI MRI and do so soon to protect humanity from unintended consequences of AGI.

One of the goals of AI MRIs that Amodei and others are working on is to catch models red-handed, to actually see those internal motivations if they exist. In his words:

To address the severity of these alignment risks, we will have to see inside AI models much more clearly than we can today. For example, one major concern is AI deception or power-seeking. The nature of AI training makes it possible that AI systems will develop, on their own, an ability to deceive humans and an inclination to seek power in a way that ordinary deterministic software never will; this emergent nature also makes it difficult to detect and mitigate such developments2. But by the same token, we’ve never seen any solid evidence in truly real-world scenarios of deception and power-seeking3 because we can’t “catch the models red-handed” thinking power-hungry, deceitful thoughts. What we’re left with is vague theoretical arguments that deceit or power-seeking might have the incentive to emerge during the training process, which some people find thoroughly compelling and others laughably unconvincing. Honestly I can sympathize with both reactions, and this might be a clue as to why the debate over this risk has become so polarized.

Could there be a devil in the black monolith? Image by Losey using Visual Muse.

Amodei and others have already created early, still primitive versions of AI MRIs, but he is hopeful that with AI help they can start to see what is really going on. Is everything good in there, or do you see a little devil? To quote Amodei:

Our long-run aspiration is to be able to look at a state-of-the-art model and essentially do a “brain scan:” a checkup that has a high probability of identifying a wide range of issues including tendencies to lie or deceive, power-seeking, flaws in jailbreaks, cognitive strengths and weaknesses of the model as a whole, and much more.  This would then be used in tandem with the various techniques for training and aligning models, a bit like how a doctor might do an MRI to diagnose a disease, then prescribe a drug to treat it, then do another MRI to see how the treatment is progressing, and so on.8  It is likely that a key part of how we will test and deploy the most capable models (for example, those at AI Safety Level 4 in our Responsible Scaling Policy framework) is by performing and formalizing such tests.

Our best path forward is with techniques like this, combined with heavy doses of human genius and inspiration. Amodei’s essay on dangers and risks of AI is very different from his prior essay on the wonders and benefits of what he called AI’s Loving Grace. See my article: Dario Amodei’s Vision: A Hopeful Future ‘Through AI’s Loving Grace,’ Is Like a Breath of Fresh Air (11/01/24). He is balanced, a true scientist-magician who, although also a CEO, is nobody’s fool. We need more like him in the AI industry. Will he save the day and figure out how the alien tech works that Hinton conjured up? Let’s hope so.

Amodei watercolor by Ralph Losey using Visual Muse.

Beyond the AI MRI Solution

Beyond the AI MRI technical solution, Amodei proposed adoption of three important policies:

  • Aggressive Interpretability R&D. Put sustained, top‑tier research funding and talent into “AI‑MRI” methods that expose exactly how advanced models represent concepts and make decisions, so we can verify safety before capabilities run loose.
  • Light‑Touch Transparency Rules. Adopt minimalist, disclosure‑focused regulations—think nutrition labels for AI—that require labs to publish safety policies and risk assessments without stifling innovation with heavy bureaucracy.
  • Export‑Control “Breathing Room.” Use targeted semiconductor and compute‑capability export limits to slow the global proliferation of cutting‑edge AI hardware just long enough for democracies to finish building robust safety guardrails.

Amodei argues that these policies should be followed to keep democracies ahead of foreign totalitarian government while we figure out the black box problem. These recommendations deserve equal billing with the MRI metaphor because they are actionable today. The chip export controls should buy humanity a critical two‑year margin in the interpretability race. In Dario Amodei’s words:

I’ve long been a proponent of export controls on chips to China because I believe that democratic countries must remain ahead of autocracies in AI. But these policies also have an additional benefit. If the US and other democracies have a clear lead in AI as they approach the “country of geniuses in a datacenter,” we may be able to “spend” a portion of that lead to ensure interpretability10 is on a more solid footing before proceeding to truly powerful AI, while still defeating our authoritarian adversaries11. Even a 1- or 2-year lead, which I believe effective and well-enforced export controls can give us, could mean the difference between an “AI MRI” that essentially works when we reach transformative capability levels, and one that does not. One year ago we couldn’t trace the thoughts of a neural network and couldn’t identify millions of concepts inside them; today we can. By contrast, if the US and China reach powerful AI simultaneously (which is what I expect to happen without export controls), the geopolitical incentives will make any slowdown at all essentially impossible.

Amodei is very concerned regarding the risk of military conflict in the race for AGI and soon thereafter. This may depend on whether an authoritarian military regime acquires significant superintelligence on weapons first and see an advantage in first strike. Regardless, Taiwan is seen by many as a likely war zone because of the unique AI chip manufacturing facilities of TMC.

Image by Losey using OpenAI’s SORA.

Generative AI is Grown, Not Built

Amodei likes to explain the black box problem in an analogy, generative AI systems are grown more than they are built:

As my friend and co-founder Chris Olah is fond of saying, generative AI systems are grown more than they are built—their internal mechanisms are “emergent” rather than directly designed. It’s a bit like growing a plant or a bacterial colony: we set the high-level conditions that direct and shape growth1, but the exact structure which emerges is unpredictable and difficult to understand or explain. Looking inside these systems, what we see are vast matrices of billions of numbers. These are somehow computing important cognitive tasks, but exactly how they do so isn’t obvious.

Click Here to see the home grown AI come alive. YouTube video and audio by Losey using SORA and other tools.

This AI may be home grown, but it is still alien because we don’t understand how it operates. This worries deep thinkers like Amodei. They are uncomfortable building and quickly improving a technology to AGI level that they don’t fully understand. AI might pursue its goals in ways that are harmful to us. It’s not like traditional software where you would have to deliberately code a program to be deceptive. It could just happen as a side effect of trying to be good at its main task.

Since we can’t directly see inside, we cannot observe deceitful thoughts if they were forming. We cannot predict how AI’s internal mechanisms will react in every situation. Can we really trust it? Heavens no! But how do we verify it is pro-human and remains that way? How do we know it has a heart, not a devil?

MRI of AI revealed a good heart. Image by Losey.

Conclusion: Vigilant Hope in a Transformative Decade

We stand on the cusp of models so capable that Anthropic’s CEO likens them to “a country of geniuses in a datacenter.” That prospect rightly sparks awe—and a twinge of vertigo. History teaches that powerful inventions rarely announce their darker side in advance; early warning signs are subtle: models that explain poorly, policies that postpone transparency “until the next release”, or economic incentives that outpace safety budgets. When you see those cracks—call them out.

Yet the same ingenuity that birthed generative AI is now inventing its own antidote. Breakthroughs in mechanistic interpretability show we can already spotlight millions of hidden concepts and even throttle rogue obsessions intentionally triggered by implanted bugs. Policy makers are awakening too: export‑control buffers, disclosure mandates, and red‑team MRIs are entering the conversation.

The last sentence in Mario Amodei essay says it well: Powerful AI will shape humanity’s destiny, and we deserve to understand our own creations before they radically transform our economy, our lives, and our future.

Who are you AI? AGI seems so promising but we don’t really know. Is this a trap? Will we be able to enjoy the cheese, get clobbered by a hidden spring or jump away at the last minute?

Click here to see a YouTube video interpretation of this image by Losey using SORA and his own audio.

I feel like concluding with a poem, one that I prompted from a still-far-from-AGI, AI, namely Chat GPT 4o. It is shown below in another AI image I prompted using Visual Muse and Photoshop.


The last words go, as usual, to the Gemini twin podcasters that summarize the article as best they can with their still tiny, but useful brains. Echoes of AI: Dario Amodei Warns of the Danger of Black Box AI that No One Understands.” Hear two fake podcaster talk about this article for about 13 minutes. They wrote the podcast, not me. 

Ralph Losey Copyright 2025. — All Rights Reserved


e-Discovery Team

LAW and TECHNOLOGY - Ralph Losey © 2006-2025

Skip to content ↓