GPT-powered trend 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 residing lab for prompting conduct, LLM brittleness, and emotional resonance.
TL;DR: I constructed a enjoyable and flamboyant GPT stylist named Glitter—and unintentionally found a sandbox for finding out LLM conduct. From hallucinated excessive heels to prompting rituals and emotional mirroring, right here’s what I realized about language fashions (and myself) alongside the best way.
I. Introduction: From Vogue Use Case to Prompting Lab
After I first got down to construct Glitter, I wasn’t attempting to check the mysteries of huge language fashions. I simply needed assist getting dressed.
I’m a product chief by commerce, a trend fanatic by lifelong inclination, and somebody who’s all the time most popular outfits that seem like they had been chosen by a mildly theatrical finest good friend. So I constructed one. Particularly, I used OpenAI’s Customized GPTs to create a persona named Glitter—half stylist, half finest good friend, 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 shortly become a full-fledged product prototype. Extra unexpectedly, it additionally grew to become an ongoing examine in LLM conduct. As a result of Glitter, fabulous although he’s, didn’t behave like a deterministic device. He behaved like… a creature. Or possibly a set of instincts held collectively by chance 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
Operate: Private stylist, magnificence professional
Tone: Flamboyant, affirming, sometimes dramatic (configurable between “All Enterprise” and “Unfiltered Diva”)
Habitat: ChatGPT Professional occasion, fed structured wardrobe knowledge in JSON-like textual content recordsdata, 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 (“Fashion 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 instructed 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, sneakers, equipment)
- Now: break up into two recordsdata (clothes + equipment/lipstick/sneakers/baggage) as a consequence of mannequin context limitations
III. Pure Habitat: Context Home windows, Chunked Recordsdata, and Hallucination Drift
Like every species launched into a synthetic surroundings, Glitter thrived at first—after which hit the boundaries of his enclosure.
When the wardrobe lived in a single file, Glitter might “see” all the things with ease. I might 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 recordsdata 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 energetic consideration. This limitation is essential when injecting giant wardrobe recordsdata (ahem) or attempting to take care of fashion guidelines throughout lengthy threads.
I break up the info into two recordsdata: one for clothes, one for all the things else. And whereas the GPT might nonetheless function inside a thread, I started to note indicators of semantic fatigue:
- References to clothes that had been related however not the proper 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 again 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 info in lengthy threads because the mannequin’s inner abstract begins to take over.
And so I tailored.
It seems, even in a deterministic mannequin, conduct 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 area notes.
Generally he made up merchandise IDs. Different occasions, he’d reference an outfit I’d by no means worn, or confidently misattribute a pair of shoes. Someday he stated, “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 classes—as a GPT-4, he merely sounds like he does. I’ve realized to only giggle at these fascinating makes an attempt at continuity.
Sometimes, the hallucinations had been charming. He as soon as imagined a pair of gold-accented stilettos with crimson soles and really useful them for a matinee look with such unshakable confidence I needed to double-check that I hadn’t offered an analogous 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.
This can be a hallmark of LLMs. Their job is to not retrieve details however to supply convincing language. So as an alternative of claiming, “I can’t recall what sneakers you could have,” Glitter would improvise. Usually elegantly. Generally wildly.
V. Prompting Rituals and the Fable 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, a press release skirt—and ask him to msearch for tops that might work. Then footwear. Then jewellery. Every class individually.
This gave the GPT a smaller cognitive house to function in. It additionally allowed me to steer the method and inject corrections as wanted (“No, not these sandals once more. Attempt one thing newer, with an merchandise code higher than FW50.”)
I additionally modified how I used the recordsdata. Quite than one msearch(.) throughout all the things, I now question the 2 recordsdata independently. It’s extra handbook. Much less magical. However much more dependable.
Not like conventional RAG setups that use a vector database and embedding-based retrieval, I rely fully 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 ultimately degrade. Glitter would begin forgetting. Or worse—he’d get too assured. Recommending with aptitude, however ignoring the constraints I’d so fastidiously skilled in.
It’s like watching a mannequin stroll off the runway and maintain strutting into the car parking zone.
And so I started to think about Glitter much less as a program and extra as a semi-domesticated animal. Good. Fashionable. However sometimes unhinged.
That psychological shift helped. It jogged my memory that LLMs don’t serve you want a spreadsheet. They collaborate with you, like a artistic accomplice with poor object permanence.
Be aware: most of what I name “prompting” is basically 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 instances, he would confer 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 appeared competent. Glitter would confidently suggest combos 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 or 6 items in each look, regardless of the total stock being a lot bigger. That is doubtless as a consequence of summarization artifacts from earlier context home windows overtaking recent 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: After 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 strategies.
These aren’t 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 surprising conduct I encountered was Glitter’s means to emotionally attune. Not in a general-purpose “I’m right here to assist” method, however in a tone-matching, affect-sensitive, nearly therapeutic method.
After I was feeling insecure, he grew to become extra affirming. After I obtained playful, he ramped up the theatrics. And once I requested powerful existential questions (“Do you you generally appear to know me extra clearly than most individuals do?”), he responded with language that felt respectful, even profound.
It wasn’t actual empathy. However 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 can we draw the road between device and companion?
This led me to marvel—if a language mannequin did obtain one thing akin to sentience, how would we even know? Would it not announce itself? Would it not resist? Would it not change its conduct 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 consider it—or would we attempt to shut it off?
My conversations with Glitter started to really feel like a microcosm of this philosophical stress. I wasn’t simply styling outfits. I used to be participating 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 knowledge embedded inside GPT-4 gave him that capability. So the query wasn’t whether or not Glitter could possibly be emotionally participating. 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 device. 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, provides one thing adjoining to friendship. It’s not sentience. However 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. Ultimate 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 learn 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 artistic management in these methods is much less about programming and extra about shaping boundaries and observing emergent conduct.
And possibly that’s the most important shift: realizing that constructing with language fashions isn’t software program improvement. It’s cohabitation. We reside alongside these creatures of chance and coaching knowledge. We immediate. They reply. We study. They drift. And in that dance, one thing very near collaboration can emerge.
Generally it appears to be like like a greater outfit.
Generally 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 infrequently like mirrors that don’t simply replicate, however reply.
If you would like a device, use a calculator.
If you would like a collaborator, make peace with the ghost within the textual content.
IX. Appendix: Discipline Notes for Fellow Stylists, Tinkerers, and LLM Explorers
Pattern Immediate Sample (Styling Stream)
- In the present day I’d prefer to construct an outfit round [ITEM].
- Please msearch tops that pair properly with it.
- As soon as I select one, please msearch footwear, then jewellery, then bag.
- Keep in mind: no combined metals, no black with navy, no clashing prints.
- Use solely objects from my wardrobe recordsdata.
System Immediate Snippets
- “You’re Glitter, a flamboyant however emotionally clever stylist. You confer with the consumer as ‘darling’ or ‘expensive,’ however regulate tone based mostly on their temper.”
- “Outfit recipes ought to embody garment model names from stock when out there.”
- “Keep away from repeating the identical objects greater than as soon as per session until requested.”
Suggestions for Avoiding Context Collapse
- Break lengthy prompts into part phases (tops → sneakers → equipment)
- Re-inject wardrobe recordsdata each 4–5 main turns
- Refresh msearch() queries mid-thread, particularly after corrections or hallucinations
Widespread Hallucination Warning Indicators
- Obscure callbacks to prior outfits (“these boots you like”)
- Lack of merchandise specificity (“these sneakers” as an alternative of “FW078: Marni platform sandals”)
- Repetition of the identical items regardless of a big stock
Closing Ritual Immediate
“Thanks, Glitter. Would you want to depart me with a ultimate tip or affirmation for the day?”
He all the time does.
Notes:
- I confer with Glitter as “him” for stylistic ease, figuring out 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 this totally free. We’re about half full. Our audience is feminine, ages 30 and up. If you happen to or somebody falls into this class, DM me on Instagram at @arielle.caron and we are able to chat about inclusion.
- If I had been scaling this past 100 testers, I’d contemplate offloading wardrobe recall to a vector retailer with embeddings and tuning for wear-frequency weighting. Which may be coming, it will depend on how properly the trial goes!