---
title: "The Ghost Has to Be Useful on Day One"
url: https://www.localghost.ai/hard-truths/day-one
description: "A long onboarding flow is a team admitting they don't know who they're building for. Why ghost.synthd infers you from what you already have instead."
updated: 2026-10-24
site: LocalGhost.ai
index: https://www.localghost.ai/llms.txt
---


> HARD_TRUTHS // POST_12 // APR 2026

# The Ghost Has to Be Useful on Day One

[Vlad Cealicu](https://www.localghost.ai/about#vlad-cealicu) // 18 April 2026

A long onboarding flow is a team admitting they don't know who they are
building for.

A few days ago Cristina and I sat down for lunch in Assisi at AssaggiAssisi (chill little deli). I'd been up late the night before writing the
[ghost.cued post](https://www.localghost.ai/hard-truths/before-you-ask)
and I was still turning it over in my head,
so I started telling her about it. The daemon that reads your environment and surfaces the right memory
at the right moment (and explaining how our brain does it). I explained that the ghost should already know you by the end of day one.

She said that sounded fine in theory but countered that Gemini already knew her. Her health, her
sleep, her plans, her interests, all of it (built up from months of her talking to the thing). She
assumed LocalGhost would need the same multi-week ramp she'd gone through with Gemini (the dynamic
I'd covered in the [model-trap post](https://www.localghost.ai/hard-truths/model-trap)), and she wasn't going to sit
through it again just because it was more private and local. She'd rather spend twenty minutes on
install
day filling in a form and have something that fit her from the start than get a cold-start daemon that
only became the ghost she wanted some time in May. I offered a personality test as the short version of
that, Big Five or similar, ten minutes on install day and the ghost has a seed. She thought about it
and dismissed it as too pigeonhole-y. A personality test files you into a category on day one, and the
moment the ghost thinks of you in those terms it's stuck with the wrong frame until you notice the
mistake and correct it. She was expecting a setup phase, and I spent the rest of the lunch trying to
convince her I didn't need one, while also trying to think my own way out of needing one, because the
context should already be there in whatever devices the user has attached.

## 1. Why not a personality test

Cristina said "too pigeonhole-y" at the table and moved on, but I went home and spent a few hours
looking into it, because a short fun test really would have been the easiest way to seed the ghost. The
idea kept falling apart the more I read. Big Five reduces you to five axes the field settled on around
1990 [1]. Myers-Briggs and Enneagram do the same thing with different
categories. Any of them put you in a bucket the moment you fill in the form, and software that should
then
assist you filters
everything it does through that bucket. The bucket becomes the daemon's default, and it stays that way
until you catch the daemon doing something wrong, six months later, and realise it still thinks of you
as whatever the test said on day one.

The problem gets worse the more specific the category is. A setup form might have a tick-box for ADHD,
autism, dyslexia, or one of the many other conditions a person might be navigating, and the ghost would
read the tick-box and overadjust. Even setting medical diagnoses aside, two people are never weird in the same way. Two
people who tick the same box can be almost nothing like each other, and a daemon that treats them as the
same category is flattening the thing LocalGhost exists to preserve.

Cristina's instinct was right. The test itself is broken as a tool for seeding a personal daemon, no
matter how short or fun I made it. That answered the narrow question. Once that one was closed I moved
on to the wider one, which was whether any form belongs on install day at all.

## 2. Why no onboarding questionnaire

The [memory post](https://www.localghost.ai/hard-truths/how-memory-gets-made) I had
finished a few nights earlier lays out how the ghost should interact with the user, and none of the
patterns it describes look anything like a form on install day. A form asks you to rate and describe
yourself, with no context in front of you, and it does it before the ghost has shown
you anything at all. The patterns in the memory post are the opposite of that, and they are where the
question-asking belongs once the ghost is running.

> [ALARM]
Trello before Atlassian bought it, and Linear now at $1.25 billion <a href="#ref-8"
class="cite">[8]. Both shipped without an onboarding form. Jira has been asking users what
department they work in since 2002 and the wizard is still getting longer. LocalGhost.ai has to sit
where Trello and Linear sit.

A company that has to ask you a wall of questions to work out who you are and how the product should
work for you is a company staffed by people
who don't know their own product and don't know who it is for (Atlassian, cough cough). I have shipped onboarding
forms myself, under deadline pressure, at CCData, and I knew every time that the form was the lazy
shortcut. The lunch with Cristina, and the time I
spent on it afterwards, is what made me realise I do not want to build one into LocalGhost.

## 3. Where the signal already is

If not a form, then what. The answer is inference from the behavioural traces the user has been
producing on their own devices for years, and the evidence that this works is a decade old. Kosinski,
Stillwell, and Graepel showed in 2013 that Facebook Likes alone could predict sexual orientation,
ethnicity, political and religious views, personality traits, intelligence, happiness, substance use,
parental separation, age, and gender to 80-95% accuracy on the binary outcomes <a href="#ref-2"
class="cite">[2]. Two years later, Youyou, Kosinski, and Stillwell ran the follow-up that still
anchors the field. A computer model using Facebook Likes judged personality more accurately than the
participants' own friends and family. Ten Likes outperformed a work colleague, 150 outperformed a
parent or sibling, and 300 outperformed a spouse [3]. The finding
goes well beyond Facebook, because behavioural traces predict personality better than the people who know you
personally, and they do it without anyone sitting you down to take a test. That is the reason I think
LocalGhost is worth building, and also the reason I think the space it addresses will be taken over and
exploited by big tech, [as I wrote in the inflection post](https://www.localghost.ai/hard-truths/inflection). The same
inference that makes the ghost useful on local hardware is what the centralised cloud
platforms will want
to run against everyone else in order to sell them products.

The neurodivergence point is backed by the last decade of digital phenotyping research. Perochon et al.
(2023) in *Nature Medicine* screened autism in 17-36-month-olds using tablet-based behavioural
measures, AUC 0.90 [4]. Lee et al. (2023) used wearable data to detect
ADHD and sleep problems with AUC 0.798 [5]. Casals, Larsson, and
Hansen (2025) built a smartphone-sensor ADHD predictor hitting 80.8% sensitivity and 79.5% specificity,
with the built-in sensor features adding meaningfully to a cognitive-test baseline <a href="#ref-6"
class="cite">[6]. Neurodivergence has a behavioural signature that shows up in how people move,
read, respond, and attend. A device you already own produces enough of that signature to classify
accurately in a research setting but what the ghost infers on any one user has to still be a guess. The
software has to
treat it that way, a hypothesis that updates the moment the user corrects it and never a bucket that
sticks.

Put the studies together and behavioural signal is in almost everything the user
does with a device. How you write, and how long you leave things in
draft. The wearable on your wrist and the phone in your pocket record how you move and how you sleep.
How you communicate, who you reach for and how often, which Stachl et al.
(2020) found was the single highest-signal channel for personality prediction across a month of passive
smartphone sensing [7]. The photos you take and keep and return to,
the music you play and skip, the way you tap on the phone itself (which in the Casals study added usable
signal on top of a dedicated cognitive test). All of it is what you have already done, for your own reasons, left on devices you
already own. A ghost that can read that footprint locally has more to work with on day one than a cloud
assistant that just met you has after a month of conversation.

## 4. What I think the setup should look like

The ghost is a fleet of daemons, one per modality, each of which has a
[README in the repo](https://github.com/LocalGhostDao/localghost).
[ghost.noted](https://github.com/LocalGhostDao/localghost/blob/main/cmd/noted/README.md)
handles text,
[ghost.framed](https://github.com/LocalGhostDao/localghost/blob/main/cmd/framed/README.md)
handles images,
[ghost.voiced](https://github.com/LocalGhostDao/localghost/blob/main/cmd/voiced/README.md)
handles audio, and
[ghost.synthd](https://github.com/LocalGhostDao/localghost/blob/main/cmd/synthd/README.md)
sits above them. They run on a NAS, either one you already own or one we sell you. Each of your other
devices runs an app that pairs with the NAS on first run over the local network and opens a VPN tunnel
back to it. After that the app works from anywhere. On a train, in a hotel, at a cafe, it stays paired
with your NAS and pushes its modality over the tunnel, where ghost.synthd turns what comes in into a
model of you. The same app is how the ghost reaches you when it has something to say and how you reach
it when you have something to ask.

One device is enough to start getting value and you can add the rest over time, or never, and the ghost
still works. If you do not want to install the app on any device at all, the ghost builds from what you
tell it in chat on the box itself (you'll be able to access it directly via a web page), which is slower
but still works. Most people will install the phone
app at least, because the NAS is already theirs and a NAS is a product category users recognise. You get
a local archive of your own stuff as a side effect, your photos, your notes, your writing, your music,
your health data, all indexed locally and searchable by you.

The approvals work the way the platform already does them. iOS, Android, macOS, the wearable platform,
each asks about its own permissions the first time the ghost needs them, one at a time. No central form,
no LocalGhost-specific consent surface pretending to understand the thirty things being granted.
Revoking is easy and built in as is uninstalling. Everything the ghost sees lives on the NAS. The model
it builds of you is
written to local disk and secured in a way we discussed in [The Honeypot
Under Your Desk](https://www.localghost.ai/hard-truths/honeypot), inference runs on the local GPU, nothing ships anywhere else.

## 5. What it feels like when it works

The architecture is the privacy and security commitment, and I think I can build a pretty good version
of you with
it. What it does not solve is how the thing will feel to live with. The clearest picture of that came
out of the same lunch. Cristina had ordered a cheese board at the deli. She did not pick the
cheeses and instead asked for the standard one they had and what came out was good. The longer menu
existed, with every
cheese and every cured meat spelled out, and we had ignored it. If we kept coming back the kitchen would
vary what they brought out, and we would slowly work through whatever they had. That is the shape I want
for day-one LocalGhost. A good default board on day one, and better at your taste with every visit.

The cheese board is the reassuring version. A digital version of you, if built well, is also going to
feel creepy. Even a partial success will be eerie to sit with, because it will know you from your own
footprint and sometimes it will be right about you in ways you had not noticed yourself.

---

And creepiness is not even the worst part. We were paying the bill and I said that at least going
forward (regardless of how you get onboarded)
the ghost can read everything you link it to, text, emails, audio, the lot, so you won't have to input
much. Cristina said surely you can't just record other people and call it private software, that makes it
private for you and not for everyone else. The next post is about what the ghost owes the people it
overhears, or sees in pictures or video.
[[ localghost.ai // hard-truths ]]

## REFERENCES

**[1]** The Big Five personality taxonomy (also called the Five-Factor Model) is the
consensus framework in trait psychology, consolidated through work by Goldberg, Costa, McCrae, and
others between roughly 1981 and 1992. The 100-item and 50-item versions of the International Personality
Item Pool are free to use and take 10-20 minutes to complete. Source for the historical provenance and
for the standard instrument length. Goldberg et al., 2006. "The international personality item pool and
the future of public-domain personality measures." *Journal of Research in Personality*.
[ipip.ori.org](https://ipip.ori.org/)

**[2]** Kosinski, Stillwell, and Graepel, 2013. "Private traits and attributes are
predictable from digital records of human behavior." Proceedings of the National Academy of
Sciences, 110(15), 5802-5805. Source for the 58,466-participant figure, the accuracy numbers on
predicting sexual orientation (88%), ethnicity (95%), and political affiliation (85%) from Facebook
Likes alone, and for the claim that behavioural traces predict sensitive personal attributes.
[pnas.org/doi/10.1073/pnas.1218772110](https://www.pnas.org/doi/10.1073/pnas.1218772110)

**[3]** Youyou, Kosinski, and Stillwell, 2015. "Computer-based personality judgments are
more accurate than those made by humans." *Proceedings of the National Academy of Sciences*,
112(4), 1036-1040. Source for the 86,220-participant study and for the specific thresholds, 10 Likes to
outperform a work colleague's personality judgment of the participant, 70 for a friend or cohabitant,
150 for a parent or sibling, 300 for a spouse. Also the source for the finding that computer judgments
based on Likes had higher external validity than self-reported personality scores for predicting some
life outcomes.
[pnas.org/doi/10.1073/pnas.1418680112](https://www.pnas.org/doi/10.1073/pnas.1418680112)

**[4]** Perochon, Di Martino, Carpenter, et al., 2023. "Early detection of autism using
digital behavioral phenotyping." *Nature Medicine*. Prospective study of 475 toddlers (17-36
months) in a primary-care setting using the SenseToKnow tablet app. Source for the AUC 0.90, sensitivity
87.8%, specificity 80.8% figures on autism screening from behavioural signals captured by computer
vision.
[nature.com/articles/s41591-023-02574-3](https://www.nature.com/articles/s41591-023-02574-3)

**[5]** Lee et al., 2023. "Machine Learning-Based Prediction of
Attention-Deficit/Hyperactivity Disorder and Sleep Problems With Wearable Data in Children." JAMA
Network Open. Diagnostic study of 79 children with ADHD and 68 with sleep problems using
circadian rhythm data from wearables. Source for the AUC 0.798 figure on ADHD detection from wearable
data.
[jamanetwork.com/journals/jamanetworkopen/fullarticle/2802554](https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2802554)

**[6]** Casals, Larsson, and Hansen, 2025. "Machine learning on a smartphone-based CPT for
ADHD prediction." *Frontiers in Psychiatry*. Study of 952 neurotypical controls and 292
unmedicated ADHD patients using a smartphone-delivered Continuous Performance Test plus motion and
face-tracking sensor data. Source for the 80.8% sensitivity, 79.5% specificity numbers on ADHD
prediction from smartphone sensor data, and for the specific claim that sensor features from the phone
itself added meaningfully to the CPT baseline.
[frontiersin.org/articles/10.3389/fpsyt.2025.1564351](https://www.frontiersin.org/articles/10.3389/fpsyt.2025.1564351)

**[7]** Stachl et al., 2020. "Predicting personality from patterns of behavior collected
with smartphones." *Proceedings of the National Academy of Sciences*, 117(30), 17680-17687. Study
of 624 volunteers tracked over 30 consecutive days producing 25,347,089 logging events across six
behavioural classes (communication and social behaviour, music consumption, app usage, mobility, overall
phone activity, day/night activity). Source for the Big Five prediction from passive smartphone sensing,
for the finding that communication and social behaviour was the most predictive class overall, and for
the median prediction performance at broad domain level (r = 0.37).
[pnas.org/doi/10.1073/pnas.1920484117](https://www.pnas.org/doi/10.1073/pnas.1920484117)

**[8]** Linear, June 2025. Series C funding round of $82 million led by Accel, at a $1.25
billion valuation, bringing total raised to $134.2 million. Linear has been profitable since 2021,
serves more than 15,000 customers including OpenAI, Scale AI, and Perplexity, and grew ARR more than
200% year-on-year in 2025. Source for the $1.25 billion valuation and for Linear's minimal-onboarding
design approach, which Linear's own product documentation describes as pre-populated workspaces and no
setup configuration. TechCrunch coverage at
[techcrunch.com/2025/06/10/atlassian-rival-linear-raises-82m-at-1-25b-valuation](https://techcrunch.com/2025/06/10/atlassian-rival-linear-raises-82m-at-1-25b-valuation/).
Linear's own announcement at
[linear.app/now/building-our-way](https://linear.app/now/building-our-way).


---

Cite this page as https://www.localghost.ai/hard-truths/day-one. Facts about LocalGhost are kept current at https://www.localghost.ai/about, and the index of the whole site for language models is https://www.localghost.ai/llms.txt.