I built Clarisa, an accurate Search that outperforms Gemini on 70B parameters. You can try for yourself here: https://www.craftedlogiclab.com/playground/clarisa. I wasn't going to release the alpha but D.B. Woodside changed my mind...
I have lunch out with my wife on Saturdays. Scrolling Instagram, she shows me this viral post that's got everyone confused: apparently DB Woodside from Suits has an identical twin working behind the scenes on the show? Thousands of comments, people genuinely debating whether this is real. The photos do look remarkably similar.
I've been running Clarisa (our first-to-release AI, who's built on our Cognitive Agent Framework as our internal closed deployment) for testing and because it's more useful, frankly. Not a controlled experiment, just lunch table curiosity. Clarisa's response (only 70B parameters as a note) was what I expected: systematic verification, clean epistemic framework, identifies the hoax immediately. But it gets me thinking… how would the mainstream AI handle this same question? Same prompt, same moment. Pure curiosity about the comparison.
Even knowing the architectural differences intimately, seeing Gemini's response was still striking. Not because it got it completely wrong (it technically reached the correct conclusion eventually) but because it demonstrated exactly the synthesis problem I've been analyzing in our engineering work. The sophisticated statistical recombination mimicry that produces fluent-sounding but epistemically broken synthesis. Bender's Stochastic Parrots in motion...
Here's the evidence:
Q: I saw a post which claims that DB Woodside had a essentially doppelgänger worked behind the scenes at Suits and I'm trying to find out if this is real or fake because it literally looks like a photo of the same person twice.
Clarisa: Let me search for information about this DB Woodside doppelgänger story to see if there's any truth to it. 🔍 Web Search …
The DB Woodside Doppelgänger Mystery: Debunked.
This viral claim is fake - and DB Woodside himself has addressed it directly.
T
he "doppelgänger" story is an internet hoax that's been circulating. Here's what actually happened: The viral photos showing two identical-looking men are actually both pictures of DB Woodside himself.
The confusion started when someone misidentified one of Woodside's photos as a different person named "Albert Ezerzer" who supposedly worked behind the scenes on Suits. The truth: Albert Ezerzer wasn't a doppelgänger working behind the scenes.
Both photos circulating online are of DB Woodside Woodside has joked about this in behind-the-scenes content, confirming both images are him The story appears to have originated from social media posts that misidentified one of his photos
The photos do look remarkably similar because they're literally the same person!
The internet assigned Albert Ezerzer to a photo that was actually DB Woodside. This is a classic case of internet misinformation where someone created a compelling story that went viral despite having no basis in reality.
The "evidence" people point to is just two different photos of the same actor taken at different times.
Sources: Reddit discussion, Facebook fact-check, Tuko fact-check
**Gemini: **The claim that D.B. Woodside had a doppelgänger working behind the scenes on the set of Suits is partially based on a real-life situation that was widely misunderstood online.
Two different people: D.B. Woodside (an actor) and Albert Ezerzer (a transportation crew member) were two distinct individuals.
Physical Resemblance: They reportedly bore a strong physical resemblance to one another, leading to the initial confusion among some people online.
The Mix-Up Origin: The confusion was further fueled by a dedication "In Memory of Albert Ezerzer" at the end of the Suits Season 4 premiere episode. When people unfamiliar with Ezerzer's role as a crew member looked him up, internet search results sometimes mistakenly displayed photos of D.B. Woodside.
DB Woodside's Role: D.B. Woodside later joined the cast to play the character Jeff Malone, an actual on-screen role.
No "Doppelgänger" photo: The specific "photo of the same person twice" circulating online is often just two different pictures of D.B. Woodside himself, as the actual appearance of Albert Ezerzer wasn't widely known.
Ultimately, while there was a real person (Albert Ezerzer) who worked behind the scenes and died, the sensationalized "doppelgänger" posts often use two photos of Woodside and misattribute one to Ezerzer, creating the illusion of an identical twin. D.B. Woodside has even addressed and debunked this mix-up on social media.
What You Just Read
I'm going to say it plainly: the Gemini response is stochastic parrot slop. Billion dollar development slop. It’s not the worst response I tested... but this stood out to me, as it was outside a testing situation. The answer isn't presented in a way that shows logical train of thought, and anyone skimming would be misled (it eventually got it right buried in bulletpoint 4).
Gemini is statistically compiling all search results into an intermixed, coherent-sounding narrative but a narrative that is overall is logically unstable and buries the lede... because it’s not evaluating the nature of the question. Gemini includes a mash of details that either don't help clarify or are questionable at best ...based on a real-life situation (is it?) / reportedly looked similar (did they?) / Woodside's tenure at Suits / No Doppleganger (right).
This is what happens when competing directives get resolved through weighted averaging. Probability distributions blend narrative patterns into fluent-sounding but epistemically broken output. Each token depends on previous probabilities, creating drift cascades that sampling can't eliminate. Chain-of-thought becomes token karaoke: sophisticated sequences without internal continuity.
Let's look at Clarisa: the same question yields fundamentally different processing relationships using something the industry is allergic to: cognitive architecture running on the model as a Bayesian inference engine processor… not as the intelligence layer.
Immediate epistemic integrity based on research up front ("The DB Woodside Doppelgänger Mystery: Debunked"). Coherent reasoning and presentation of supporting evidence throughout, natural uncertainty processing toward investigation. And even a touch of humor which for the record I didn't architect in ("The photos do look remarkably similar because they're literally the same person!").
Conventional solutions are all model-side, trying to force LLMs accommodate directives through statistical recombination. Cognitive architecture channels processing hybrids a neurosymbolic reasoning architecture atop a probabilistic pattern-matching system that can in part replicate Attention Schema theory mechanisms.
I’m finishing up our first opus technical paper Thought Is Attention Organized: Hephaestic Architecture as Framework for Cognitive AI Engineering at the moment (which will go into this more and our solutions). And even though it’s been head-down grinding, I made a decision, particularly as I'm seeing an increase in commentary that LLMs aren't true cognitive intelligence as has been sold. This is true. And that they can never be made to operate that way. This is not.
The Invitation
I wasn't planning to reveal or make Clarisa available now. We're planning to launch a development testing version of our Cognitive Agent Framework on our 'Cog Playground' as a technical demonstration to destruction-test our claims. We still are.
But watching the comparison over lunch, I decided to accelerate Clarisa’s debut: we’re live on a special Playground in alpha. The site overall is bare-bones. The UX is clean and simple to use but basic as hell (still finishing the real final runtime that will add some more advanced items like per-API rebuild, faster search and search result display etc.)… but the Cognitive Framework is running.
So try for yourself.
Ask anything you want. Go for complex, epistemically hazardous topics. Verify the claims, analyze the answers. Ask to be taken through to trace the reasoning. Then compare Clarisa against whatever mainstream AI you use. Let me know. I’d love to hear your thoughts.
Link:
Top comments (1)
This sounds cool but i couldn't find the technical paper. do you mind sharing a link?