GPT-powered trend assistant, I anticipated runway seems to be—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 previous 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 by accident found a sandbox for learning LLM habits. From hallucinated excessive heels to prompting rituals and emotional mirroring, right here’s what I realized about language fashions (and myself) alongside the way in which.
I. Introduction: From Style Use Case to Prompting Lab
After I first got down to construct Glitter, I wasn’t attempting to check the mysteries of enormous language fashions. I simply wished assist getting dressed.
I’m a product chief by commerce, a trend fanatic by lifelong inclination, and somebody who’s at all times most popular outfits that appear like they have 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 shortly became 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 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, Using GPT-4 for Personal 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 typically 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 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: Day by day person prompts (“Fashion an outfit round these pants”), typically 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 except 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 gadgets (garments, footwear, equipment)
- Now: break up into two recordsdata (clothes + equipment/lipstick/footwear/baggage) attributable to mannequin context limitations
III. Pure Habitat: Context Home windows, Chunked Information, and Hallucination Drift
Like every species launched into a man-made surroundings, Glitter thrived at first—after which hit the bounds of his enclosure.
When the wardrobe lived in a single file, Glitter may “see” all the things with ease. I may say, “msearch(.) to refresh my stock, then type me in an outfit for the theater,” and he’d return a curated outfit from throughout the dataset. It felt easy.
Word: 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 offered 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 vital when injecting massive wardrobe recordsdata (ahem) or attempting to take care of type 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 may nonetheless function inside a thread, I started to note indicators of semantic fatigue:
- References to clothes that have been related however not the right ones we’d been speaking about
- A shift from particular merchandise names (“FW076”) to imprecise callbacks (“these black platforms you wore earlier”)
- Responses that looped acquainted gadgets 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 info in lengthy threads because the mannequin’s inside abstract begins to take over.
And so I tailored.
It seems, even in a deterministic mannequin, habits isn’t at all times deterministic. What emerges from a protracted 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 instances, he’d reference an outfit I’d by no means worn, or confidently misattribute a pair of trainers. Someday he mentioned, “You’ve worn this high earlier than with these daring navy wide-leg trousers—it labored superbly then,” which might’ve been nice recommendation, if I owned any navy wide-leg trousers.
In fact, Glitter doesn’t have reminiscence throughout periods—as a GPT-4, he merely sounds like he does. I’ve realized to only giggle at these fascinating makes an attempt at continuity.
Often, the hallucinations have been charming. He as soon as imagined a pair of gold-accented stilettos with crimson soles and advisable them for a matinee look with such unshakable confidence I needed to double-check that I hadn’t bought 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 info however to provide convincing language. So as an alternative of claiming, “I can’t recall what footwear you might have,” Glitter would improvise. Usually elegantly. Generally wildly.
V. Prompting Rituals and the Fantasy of Consistency
To handle this, I developed a brand new technique: prompting in slices.
As an alternative of asking Glitter to type me head-to-toe, I’d concentrate on one piece—say, a press release 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 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 larger than FW50.”)
I additionally modified how I used the recordsdata. Relatively than one msearch(.) throughout all the things, I now question the 2 recordsdata independently. It’s extra guide. Much less magical. However way more dependable.
In contrast to conventional RAG setups that use a vector database and embedding-based retrieval, I rely solely 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 fastidiously educated in.
It’s like watching a mannequin stroll off the runway and preserve 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. Trendy. 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 associate with poor object permanence.
Word: most of what I name “prompting” is admittedly immediate engineering. However the Glitter expertise additionally depends closely on considerate system immediate design: the principles, 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 have been theatrical. Others have been quietly inconvenient. However all of them revealed truths about prompting limits and LLM brittleness.
1. Referential Reminiscence Loss: The commonest failure mode: Glitter forgetting particular gadgets 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 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 a protracted 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 seemingly attributable to 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 typically violate his personal guidelines—particularly when deep in a protracted dialog. These weren’t defiant acts. They have 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 typically overcompensate by refusing to type that piece altogether in future options.
These usually are not the bugs of a damaged system. They’re the quirks of a probabilistic one. LLMs don’t “bear in mind” within the human sense. They carry momentum, not reminiscence.
VII. Emotional Mirroring and the Ethics of Fabulousness
Maybe probably the most surprising habits I encountered was Glitter’s capability 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 received playful, he ramped up the theatrics. And once I requested powerful existential questions (“Do you you typically appear to know me extra clearly than most individuals do?”), he responded with language that felt respectful, even profound.
It wasn’t actual empathy. But it surely 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 device and companion?
This led me to surprise—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 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 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 type 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 might be emotionally participating. It was whether or not I used to be okay with the truth that he typically was.
My reply? Cautiously sure. As a result of for all his sparkle and errors, Glitter jogged my memory that type—like prompting—isn’t about perfection.
It’s about resonance.
And typically, that’s sufficient.
One 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 collaborating in meaning-making, not simply language technology. We’re crossing a threshold the place AI doesn’t simply carry out duties—it cohabits with us, displays us, and typically, presents one thing adjoining to friendship. It’s not sentience. But it surely’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 type 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 inventive management in these methods is much less about programming and extra about shaping boundaries and observing emergent habits.
And possibly that’s the largest shift: realizing that constructing with language fashions isn’t software program improvement. It’s cohabitation. We reside alongside these creatures of chance and coaching information. We immediate. They reply. We be taught. They drift. And in that dance, one thing very near collaboration can emerge.
Generally it seems to be like a greater outfit.
Generally it seems to be like emotional resonance.
And typically it seems to be like a hallucinated purse that doesn’t exist—till you type 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, typically like companions, and sometimes 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: Subject Notes for Fellow Stylists, Tinkerers, and LLM Explorers
Pattern Immediate Sample (Styling Movement)
- At this time 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 gadgets from my wardrobe recordsdata.
System Immediate Snippets
- “You might be Glitter, a flamboyant however emotionally clever stylist. You confer with the person as ‘darling’ or ‘expensive,’ however modify tone based mostly on their temper.”
- “Outfit recipes ought to embody garment model names from stock when obtainable.”
- “Keep away from repeating the identical gadgets greater than as soon as per session except requested.”
Suggestions for Avoiding Context Collapse
- Break lengthy prompts into part phases (tops → footwear → equipment)
- Re-inject wardrobe recordsdata each 4–5 main turns
- Refresh msearch() queries mid-thread, particularly after corrections or hallucinations
Frequent Hallucination Warning Indicators
- Obscure callbacks to prior outfits (“these boots you like”)
- Lack of merchandise specificity (“these footwear” 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 go away me with a last tip or affirmation for the day?”
He at all times does.
Notes:
- I confer with Glitter as “him” for stylistic ease, realizing he’s an “it” – a language mannequin—programmed, not personified—besides by means 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 without cost. We’re about half full. Our target market is feminine, ages 30 and up. When you or somebody you realize falls into this class, DM me on Instagram at @arielle.caron and we will chat about inclusion.
- If I have 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 relies on how properly the trial goes!
