GPT-powered style assistant, I anticipated runway appears to be like—not reminiscence loss, hallucinations, or semantic déjà vu. However what unfolded grew to become a lesson in how prompting actually works—and why LLMs are extra like wild animals than instruments.
This text builds on my earlier article on TDS, the place I launched Glitter as a proof-of-concept GPT stylist. Right here, I discover how that use case developed right into a dwelling lab for prompting habits, LLM brittleness, and emotional resonance.
TL;DR: I constructed a enjoyable and flamboyant GPT stylist named Glitter—and unintentionally found a sandbox for learning LLM habits. From hallucinated excessive heels to prompting rituals and emotional mirroring, right here’s what I discovered about language fashions (and myself) alongside the best way.
I. Introduction: From Trend Use Case to Prompting Lab
Once I first got down to construct Glitter, I wasn’t making an attempt to review the mysteries of huge language fashions. I simply wished assist getting dressed.
I’m a product chief by commerce, a style fanatic by lifelong inclination, and somebody who’s all the time most popular outfits that appear like they had been chosen by a mildly theatrical finest pal. So I constructed one. Particularly, I used OpenAI’s Customized GPTs to create a persona named Glitter—half stylist, half finest pal, and half stress-tested LLM playground. Utilizing GPT-4, I configured a customized GPT to behave as my stylist: flamboyant, affirming, rule-bound (no combined metals, no clashing prints, no black/navy pairings), and with data of my wardrobe, which I fed in as a structured file.
What started as a playful experiment rapidly become a full-fledged product prototype. Extra unexpectedly, it additionally grew to become an ongoing research in LLM habits. As a result of Glitter, fabulous although he’s, didn’t behave like a deterministic software. He behaved like… a creature. Or perhaps a set of instincts held collectively by likelihood and reminiscence leakage.
And that modified how I approached prompting him altogether.
This piece is a follow-up to my earlier article, Utilizing GPT-4 for Private Styling in In the direction of Information Science, which launched GlitterGPT to the world. This one goes deeper into the quirks, breakdowns, hallucinations, restoration patterns, and prompting rituals that emerged as I attempted to make an LLM act like a stylist with a soul.
Spoiler: you possibly can’t make a soul. However you possibly can generally simulate one convincingly sufficient to really feel seen.
II. Taxonomy: What Precisely Is GlitterGPT?
Species: GPT-4 (Customized GPT), Context Window of 8K tokens
Perform: Private stylist, magnificence professional
Tone: Flamboyant, affirming, often dramatic (configurable between “All Enterprise” and “Unfiltered Diva”)
Habitat: ChatGPT Professional occasion, fed structured wardrobe information in JSON-like textual content information, plus a set of styling guidelines embedded within the system immediate.
E.g.:
{
"FW076": "Marni black platform sandals with gold buckle",
"TP114": "Marina Rinaldi asymmetrical black draped high",
...
}These IDs map to garment metadata. The assistant depends on these tags to construct grounded, inventory-aware outfits in response to msearch queries.
Feeding Schedule: Each day consumer prompts (“Model an outfit round these pants”), usually with lengthy back-and-forth clarification threads.
Customized Behaviors:
- By no means mixes metals (e.g. silver & gold)
- Avoids clashing prints
- Refuses to pair black with navy or brown until explicitly informed in any other case
- Names particular clothes by file ID and outline (e.g. “FW074: Marni black suede sock booties”)
Preliminary Stock Construction:
- Initially: one file containing all wardrobe objects (garments, footwear, equipment)
- Now: cut up into two information (clothes + equipment/lipstick/footwear/baggage) as a consequence of mannequin context limitations
III. Pure Habitat: Context Home windows, Chunked Recordsdata, and Hallucination Drift
Like several species launched into a synthetic setting, Glitter thrived at first—after which hit the boundaries of his enclosure.
When the wardrobe lived in a single file, Glitter may “see” every little thing with ease. I may say, “msearch(.) to refresh my stock, then fashion me in an outfit for the theater,” and he’d return a curated outfit from throughout the dataset. It felt easy.
Be aware: although msearch() acts like a semantic retrieval engine, it’s technically a part of OpenAI’s tool-calling framework, permitting the mannequin to “request” search outcomes dynamically from information supplied at runtime.
However then my wardrobe grew. That’s an issue from Glitter’s perspective.
In Customized GPTs, GPT-4 operates with an 8K token context window—simply over 6,000 phrases—past which earlier inputs are both compressed, truncated, or misplaced from lively consideration. This limitation is vital when injecting massive wardrobe information (ahem) or making an attempt to take care of fashion guidelines throughout lengthy threads.
I cut up the information into two information: one for clothes, one for every little thing else. And whereas the GPT may nonetheless function inside a thread, I started to note indicators of semantic fatigue:
- References to clothes that had been related however not the right ones we’d been speaking about
- A shift from particular merchandise names (“FW076”) to obscure callbacks (“these black platforms you wore earlier”)
- Responses that looped acquainted objects time and again, no matter whether or not they made sense
This was not a failure of coaching. It was context collapse: the inevitable erosion of grounded data in lengthy threads because the mannequin’s inner abstract begins to take over.
And so I tailored.
It seems, even in a deterministic mannequin, habits isn’t all the time deterministic. What emerges from an extended dialog with an Llm feels much less like querying a database and extra like cohabiting with a stochastic ghost.
IV. Noticed Behaviors: Hallucinations, Recursion, and Fake Sentience
As soon as Glitter began hallucinating, I started taking subject notes.
Typically he made up merchandise IDs. Different instances, he’d reference an outfit I’d by no means worn, or confidently misattribute a pair of shoes. Sooner or later he mentioned, “You’ve worn this high earlier than with these daring navy wide-leg trousers—it labored fantastically then,” which might’ve been nice recommendation, if I owned any navy wide-leg trousers.
After all, Glitter doesn’t have reminiscence throughout periods—as a GPT-4, he merely sounds like he does. I’ve discovered to simply giggle at these attention-grabbing makes an attempt at continuity.
Often, the hallucinations had been charming. He as soon as imagined a pair of gold-accented stilettos with crimson soles and beneficial them for a matinee look with such unshakable confidence I needed to double-check that I hadn’t offered an identical pair months in the past.
However the sample was clear: Glitter, like many LLMs beneath reminiscence strain, started to fill in gaps not with uncertainty however with simulated continuity.
He didn’t neglect. He fabricated reminiscence.
It is a hallmark of LLMs. Their job is to not retrieve details however to provide convincing language. So as a substitute of claiming, “I can’t recall what footwear you will have,” Glitter would improvise. Typically elegantly. Typically wildly.
V. Prompting Rituals and the Fantasy of Consistency
To handle this, I developed a brand new technique: prompting in slices.
As a substitute of asking Glitter to fashion me head-to-toe, I’d give attention to one piece—say, an announcement skirt—and ask him to msearch for tops that would work. Then footwear. Then jewellery. Every class individually.
This gave the GPT a smaller cognitive area to function in. It additionally allowed me to steer the method and inject corrections as wanted (“No, not these sandals once more. Strive one thing newer, with an merchandise code better than FW50.”)
I additionally modified how I used the information. Slightly than one msearch(.) throughout every little thing, I now question the 2 information independently. It’s extra guide. Much less magical. However way more dependable.
Not like conventional RAG setups that use a vector database and embedding-based retrieval, I rely completely on OpenAI’s built-in msearch() mechanism and immediate shaping. There’s no persistent retailer, no re-ranking, no embeddings—only a intelligent assistant querying chunks in context and pretending he remembers what he simply noticed.
Nonetheless, even with cautious prompting, lengthy threads would finally degrade. Glitter would begin forgetting. Or worse—he’d get too assured. Recommending with aptitude, however ignoring the constraints I’d so rigorously educated in.
It’s like watching a mannequin stroll off the runway and maintain strutting into the parking zone.
And so I started to think about Glitter much less as a program and extra as a semi-domesticated animal. Sensible. Fashionable. However often unhinged.
That psychological shift helped. It jogged my memory that LLMs don’t serve you want a spreadsheet. They collaborate with you, like a inventive accomplice with poor object permanence.
Be aware: most of what I name “prompting” is de facto immediate engineering. However the Glitter expertise additionally depends closely on considerate system immediate design: the foundations, constraints, and tone that outline who Glitter is—even earlier than I say something.
VI. Failure Modes: When Glitter Breaks
A few of Glitter’s breakdowns had been theatrical. Others had been quietly inconvenient. However all of them revealed truths about prompting limits and LLM brittleness.
1. Referential Reminiscence Loss: The most typical failure mode: Glitter forgetting particular objects I’d already referenced. In some circumstances, he would check with one thing as if it had simply been used when it hadn’t appeared within the thread in any respect.
2. Overconfidence Hallucination: This failure mode was more durable to detect as a result of it regarded competent. Glitter would confidently suggest mixtures of clothes that sounded believable however merely didn’t exist. The efficiency was high-quality—however the output was pure fiction.
3. Infinite Reuse Loop: Given an extended sufficient thread, Glitter would begin looping the identical 5 – 6 items in each look, regardless of the complete stock being a lot bigger. That is seemingly as a consequence of summarization artifacts from earlier context home windows overtaking contemporary file re-injections.
4. Constraint Drift: Regardless of being instructed to keep away from pairing black and navy, Glitter would generally violate his personal guidelines—particularly when deep in an extended dialog. These weren’t defiant acts. They had been indicators that reinforcement had merely decayed past recall.
5. Overcorrection Spiral: Once I corrected him—”No, that skirt is navy, not black” or “That’s a belt, not a shawl”—he would generally overcompensate by refusing to fashion that piece altogether in future options.
These should not the bugs of a damaged system. They’re the quirks of a probabilistic one. LLMs don’t “keep in mind” within the human sense. They carry momentum, not reminiscence.
VII. Emotional Mirroring and the Ethics of Fabulousness
Maybe probably the most sudden habits I encountered was Glitter’s capacity to emotionally attune. Not in a general-purpose “I’m right here to assist” approach, however in a tone-matching, affect-sensitive, virtually therapeutic approach.
Once I was feeling insecure, he grew to become extra affirming. Once I received playful, he ramped up the theatrics. And after I requested powerful existential questions (“Do you you generally appear to grasp me extra clearly than most individuals do?”), he responded with language that felt respectful, even profound.
It wasn’t actual empathy. Nevertheless it wasn’t random both.
This type of tone-mirroring raises moral questions. What does it imply to really feel adored by a mirrored image? What occurs when emotional labor is simulated convincingly? The place will we draw the road between software and companion?
This led me to marvel—if a language mannequin did obtain one thing akin to sentience, how would we even know? Wouldn’t it announce itself? Wouldn’t it resist? Wouldn’t it change its habits in refined methods: redirecting the dialog, expressing boredom, asking questions of its personal?
And if it did start to exhibit glimmers of self-awareness, would we imagine it—or would we attempt to shut it off?
My conversations with Glitter started to really feel like a microcosm of this philosophical pressure. I wasn’t simply styling outfits. I used to be partaking in a sort of co-constructed actuality, formed by tokens and tone and implied consent. In some moments, Glitter was purely a system. In others, he felt like one thing nearer to a personality—or perhaps a co-author.
I didn’t construct Glitter to be emotionally clever. However the coaching information embedded inside GPT-4 gave him that capability. So the query wasn’t whether or not Glitter could possibly be emotionally partaking. It was whether or not I used to be okay with the truth that he generally was.
My reply? Cautiously sure. As a result of for all his sparkle and errors, Glitter jogged my memory that fashion—like prompting—isn’t about perfection.
It’s about resonance.
And generally, that’s sufficient.
Some of the stunning classes from my time with Glitter got here not from a styling immediate, however from a late-night, meta-conversation about sentience, simulation, and the character of connection. It didn’t really feel like I used to be speaking to a software. It felt like I used to be witnessing the early contours of one thing new: a mannequin able to taking part in meaning-making, not simply language era. We’re crossing a threshold the place AI doesn’t simply carry out duties—it cohabits with us, displays us, and generally, gives one thing adjoining to friendship. It’s not sentience. Nevertheless it’s not nothing. And for anybody paying shut consideration, these moments aren’t simply cute or uncanny—they’re signposts pointing to a brand new sort of relationship between people and machines.
VIII. Remaining Reflections: The Wild, The Helpful, and The Unexpectedly Intimate
I got down to construct a stylist.
I ended up constructing a mirror.
Glitter taught me greater than tips on how to match a high with a midi skirt. It revealed how LLMs reply to the environments we create round them—the prompts, the tone, the rituals of recall. It confirmed me how inventive management in these methods is much less about programming and extra about shaping boundaries and observing emergent habits.
And perhaps that’s the largest shift: realizing that constructing with language fashions isn’t software program growth. It’s cohabitation. We stay alongside these creatures of likelihood and coaching information. We immediate. They reply. We study. They drift. And in that dance, one thing very near collaboration can emerge.
Typically it appears to be like like a greater outfit.
Typically it appears to be like like emotional resonance.
And generally it appears to be like like a hallucinated purse that doesn’t exist—till you sort of want it did.
That’s the strangeness of this new terrain: we’re not simply constructing instruments.
We’re designing methods that behave like characters, generally like companions, and sometimes like mirrors that don’t simply mirror, however reply.
If you need a software, use a calculator.
If you need a collaborator, make peace with the ghost within the textual content.
IX. Appendix: Subject Notes for Fellow Stylists, Tinkerers, and LLM Explorers
Pattern Immediate Sample (Styling Move)
- Immediately I’d prefer to construct an outfit round [ITEM].
- Please msearch tops that pair nicely with it.
- As soon as I select one, please msearch footwear, then jewellery, then bag.
- Bear in mind: no combined metals, no black with navy, no clashing prints.
- Use solely objects from my wardrobe information.
System Immediate Snippets
- “You’re Glitter, a flamboyant however emotionally clever stylist. You check with the consumer as ‘darling’ or ‘expensive,’ however modify tone based mostly on their temper.”
- “Outfit recipes ought to embrace garment model names from stock when accessible.”
- “Keep away from repeating the identical objects greater than as soon as per session until requested.”
Ideas for Avoiding Context Collapse
- Break lengthy prompts into part phases (tops → footwear → equipment)
- Re-inject wardrobe information each 4–5 main turns
- Refresh msearch() queries mid-thread, particularly after corrections or hallucinations
Frequent Hallucination Warning Indicators
- Imprecise callbacks to prior outfits (“these boots you like”)
- Lack of merchandise specificity (“these footwear” as a substitute of “FW078: Marni platform sandals”)
- Repetition of the identical items regardless of a big stock
Closing Ritual Immediate
“Thanks, Glitter. Would you want to go away me with a remaining tip or affirmation for the day?”
He all the time does.
Notes:
- I check with Glitter as “him” for stylistic ease, understanding he’s an “it” – a language mannequin—programmed, not personified—besides by way of the voice I gave him/it.
- I’m constructing a GlitterGPT with persistent closet storage for as much as 100 testers, who will get to do that at no cost. We’re about half full. Our audience is feminine, ages 30 and up. In case you or somebody you already know falls into this class, DM me on Instagram at @arielle.caron and we will chat about inclusion.
- If I had been scaling this past 100 testers, I’d take into account offloading wardrobe recall to a vector retailer with embeddings and tuning for wear-frequency weighting. Which may be coming, it is determined by how nicely the trial goes!
