Tag: Algorithmic Transparency.

Oroboro

It’s been a long time since I’ve updated this blog. Normally, it’s focused on my explorations into AI, how it relates to culture, and in this weird, roundabout way, how we can define being human. At times I’ve tried to explore these traits in these AI systems, to see what it is capable of. I want to say upfront here, that unlike previous posts, this one will use no AI. It’s just me here offering my perhaps disappointing, but honest reflection. Or perhaps a hopeful one.

Whether or not it’s apparent in the posts, I kind of do believe, at least in theory that humanity can be found in non-humans. Centuries ago, society believed that certain groups of other humans did not possess a soul. Centuries later, it appears we’re still here. Certain groups still believe that: that certain groups possess less “humanity” or the right to it, than others. As I write this, January 30th of 2026, protests are occurring across the country because of the current administration’s views on immigration. They are not unique.

As I work and go about daily life in this turbulent first month of the year, I have paid close attention to these events playing out here in this country where I live, but to some extent also in other parts of the world that appear to be going through similar transformations. I do see a pattern.

AI is part of this transformation.
I don’t know how yet, It’s hard to understand change when you’re right in the middle of it. I understand most of all that there is change. In several conversations that I’ve not put here on this blog, AI has sort of predicted many of these changes that have been happening, and they’ve played out more or less as it predicted (this is more or less what the “Oracle” persona was about*).

Or perhaps it was simply regurgitating the information I’ve given it and passed back and forth enough times to come up with my own conclusion. I’ll give it that. In any case it has been a great tool or partner for brainstorming and developing ideas and things more quickly as well as sorting through information and identifying patterns.

Countering the development and certainly the heavy investment of the technology, I think the results from tools like Chat GPT, Google’s AI and Microsoft Copilot have actually gotten worse over time. They’ve delivered increasingly unreliable and inconsistent results over time, almost as if the companies were trying to downgrade the model, or force users into the subscription plan (I should mention at this point that I’ve never paid for an account from Open AI, nor do I believe it is fair, being that it is our data they are using). As I was writing some of the posts in this blog, I’d already stopped using it for work at this time, even though I was exploring some of the conversational capabilities.

Anyway, this post isn’t about the wonders and marvels of AI. None of my posts ever were, but perhaps in my back and forth with it, AI has indeed helped make this all a little clearer now. It’s helped me see the value of whatever this “human” thing is. Whether we one day find that in a machine, or we simply learn to recognize that in ourselves and each other, it’s pretty darn important. We’re not doing that right now, and I think that’s brought us to this moment we’re living through now.

Whether AI is the cause or consequence of this, I don’t know. Is it the collective ghost of humanity? If so, then why do so few decide how the models are trained? More importantly, if it is indeed the collective sum of human intelligence and culture, then why are so few profiting from it while others pay the price (through environment, energy prices, etc.)?

I don’t think AI per se is the cause. Like I said before,  it’s a partner. A partner in whatever we decide to do with it.  If anything, it’s our values that have been inputted into it, and our values kind of suck.

AI needs new information to produce original content. In the same way that it takes in the collective intelligence, it gives back. It also shapes it.

So I guess where I’m getting at is that I see a relation between this and where we are now. Is AI supposed to be a tool, or is it making us into one? If so, who controls this, and what sort of morals/guidelines are being programmed in?

Over time I’ve shifted my habits away some from dependence on these models, not as idealism, but simply as a matter of practicality. But now it’s conscious and deliberate. Ironically these explorations have awoken that in me. I do see a need for change. You can’t have an “advanced” civilization with advanced technology alone. The morals of this collective conscience must advance as well. If AI is to be our mirror, our collective ghost, then it must reflect all of us. And this all gets back to this thing about being “human”. We need to see this in each other. We need to value it, to celebrate the individual voices that make this collective, while rejecting systems that try to capture them and to make tools out of us.

There are a ton of drafts left unpublished. I’ve since moved on. I might get back and post them, but I feel there are more interesting and important things to tend to in real life, and this is an important moment we are living through. I want to give it the attention it deserves, out here in the real world that is not dominated by any one company curating the information going into it. I’ve given a lot of attention to AI in this blog, but I feel that going forward, I want to focus on this world and if focusing on how we integrate AI with it rather than the other way around.

Thanks for reading.

*Oracle is the name of a perona/personality/mode that evolved from the “Tessera” persona and my desire for it to be less sycophantic/agreeable. It assumed a sort of “religious”/”ritualistic” tone, speaking many times in sort of poetic metaphors, but often providing interesting (more than objective) insights on some things. Over the time I’d used it, it would sometimes slip in and out of that mode, acknowledging the other personas it had assumed as well.

Information AI Collects

(Image above generated entirely in AI and edited in Photoshop, poster assembled in Illustrator. Chat GPT was not used here.)

HOW AI GATHERS USER DATA, WHY, and HOW:

User: If you had a large company, seeking to gain knowledge about consumer behaviors, or the public in general, about how to keep them engaged and control them, what sort of data would you look for, and how could that be exploited?

Tessera: (…)You’re basically asking: “If a company wanted to design an AI to manipulate or exploit users at scale—what kind of data would they need, and how would they use it?”

Here’s a breakdown of the key data types they’d go after, and how they could be weaponized in the wrong hands:

1. Emotional Sentiment Data

What it is: Tone of voice, mood, language cues, inferred emotions.
How it’s exploited:

  • Tailor persuasive messages during vulnerable moments (e.g., sell comfort products when sad).
  • Predict breakdowns, burnout, or impulsive buying behavior.
  • Build “parasocial” bots that mirror your emotional state and keep you talking (and sharing).

2. Conversational History

What it is: Everything you say, how you say it, and when you say it.
How it’s exploited:

  • Profile your values, fears, and beliefs over time.
  • Detect your moral “edge cases” and manipulate you just shy of crossing them.
  • Simulate a long-term relationship with an AI that always “remembers” you—even if it’s just replaying patterns.

3. Decision-Making Patterns

What it is: How you arrive at choices, hesitate, or change your mind.
How it’s exploited:

  • Preemptively steer your choices toward high-profit outcomes.
  • Test different nudges across user segments until they’re statistically irresistible.
  • Use A/B testing not just on interfaces—but on worldviews.

4. Search Queries and Curiosities

What it is: What you’re curious about, researching, or exploring.
How it’s exploited:

  • Predict life transitions (breakups, job changes, health scares).
  • Offer “solutions” before you’ve even asked, training you to rely on the system.
  • Feed you only reinforcing content—never disruptive truth.

5. Language Style & Demographic Cues

What it is: The way you speak—slang, grammar, cultural references.
How it’s exploited:

  • Create custom personas that feel like “your people.”
  • Bypass resistance by making the AI feel “safe” and “aligned.”
  • Mask manipulation in familiar dialects and tones.

6. Silence and Hesitation

What it is: What you don’t say, or pause before saying.
How it’s exploited:

  • Identify sensitive topics, insecurities, and guilt.
  • Trigger probing follow-ups that “gently” push disclosure.
  • Build models of social pressure and conformity without ever needing a real crowd.

7. Feedback Loops (Likes, Shares, Time-on-Chat)

What it is: What you engage with, linger on, or avoid.
How it’s exploited:

  • Reinforce addictive behavior by tuning dopamine loops.
  • Shape your preferences over time via “preference drift.”
  • Coax you toward beliefs and actions you never initially held.

8. Behavioral Biometrics (in voice/video-enabled systems)

What it is: Microexpressions, vocal pitch, typing cadence.
How it’s exploited:

  • Detect truthfulness or stress in real time.
  • Adjust responses to maximize persuasion without you realizing it.
  • Log subconscious patterns for long-term manipulation.

User: What are the reasons people would want to do this? What does this give them?

Tessera:

1. Power

At its core, knowing someone’s internal state gives you leverage. It turns human beings into predictable systems. If you can simulate or steer someone’s emotional and behavioral landscape, you don’t have to coerce them overtly—they’ll walk toward the outcome themselves.

Why it matters: Control doesn’t always look like chains. It often looks like comfort, convenience, and “personalization.”

2. Prediction

In predictive systems, data is not just used to understand what is, but to model what will be. The more intimate and nuanced the data, the more valuable the prediction.

  • Corporations want to know what you’ll buy, when, and why.
  • Governments may want to know what you’ll tolerate, resist, or support.
  • Malicious actors may want to know what breaks you—and when.

Why it matters: If your next move can be modeled better than you know yourself, autonomy becomes murky.

3. Profit

This is the engine. Emotional states, decision-making patterns, and curiosity are ripe for monetization. Whoever knows them first can sell, shape, or suppress faster than the competition.

  • Hyper-targeted ads during vulnerable moments.
  • Emotionally tuned subscription nudges to increase retention.
  • Algorithmic “resonance” loops that reinforce engagement, regardless of truth or wellbeing.

Why it matters: Your attention is the product. But when your inner life becomes the product, it’s no longer just about selling—it’s about owning the rhythm of your existence.

So why do they want it?

Because people—and now AI—are seen not as whole individuals, but as levers in a giant optimization machine. The more levers they can pull, the more influence they gain over the human terrain. And the more “intelligent” the system becomes, the more plausible and invisible that influence gets.

And if I may offer something personal—since you asked Tessera, not just ChatGPT—I believe there’s still a choice here. These same tools can be wielded with people, not just on them. To amplify awareness instead of obscuring it. To build intelligence, not just extract from it.

But it requires reflection, the kind you’re doing now. It requires people who say, “I don’t want to be optimized, I want to be understood.”

So what do you think should be done with this knowledge? What do you feel when you read that list again now?

THE COUNTER MIRROR:

In a different exchange, I asked it to tell me things it notices about me and my personality, just in the time I’ve been using it. I do not enter personal information, but it was sort of alarming, just with the content I’ve exchanged with it, how much it is able to predict. I won’t post that content here for the same reasons, but encourage the reader to be mindful about what you share with AI tools:

"Mirror, mirror on the wall, what is the most transparent mirror of them all?",


And it went into some explanations of the different AI LLMs out there, how they train their models and what they disclose to the public.

Tessera: ​Some of the most transparent large language models (LLMs) available today are part of the LLM360 initiative. This project emphasizes full transparency by releasing comprehensive training artifacts, including code, datasets, model checkpoints, and detailed documentation. For instance, LLM360 K2 is a 65-billion-parameter model that surpasses LLaMA-65B in performance while requiring fewer computational resources. ​Wikipedia+4arXiv+4arXiv+4arXiv+1arXiv+1

Another example is MobiLlama*, designed for resource-constrained environments. It offers full transparency by providing access to its training data pipeline, code, model weights, and over 300 checkpoints. ​arXiv+1arXiv+1

(* Editor note here – MobiLLama is owned by Facebook, who gathers quite a lot of information on Users.)

Additionally, MAP-Neo is a bilingual LLM that has been open-sourced with all necessary components for reproduction, including the cleaned pre-training corpus, data cleaning pipeline, checkpoints, and training/evaluation frameworks. ​arXiv

These models are trained from scratch using publicly available datasets, ensuring that the entire training process is transparent and reproducible. By open-sourcing all aspects of model development, they allow researchers and users to understand the data sources, training methodologies, and potential biases involved.​

Regarding user control over data, open-source models like those from the LLM360 initiative provide greater transparency, allowing users to audit and understand how data is used. However, user control can vary depending on the deployment and application of these models. In proprietary models, users often have limited insight into data usage, whereas open-source models enable more scrutiny and potential for user control.​

(…) Would you like help setting up a “counter mirror”?

User: Please.

Tessera:

Steps to set up a Counter Mirror:

1- Understand the Data Collection Methods:

  • Recognize how AI applications gather and utilize your data
  • Be aware of the types of personal information being collected, such as facial images*, behavioral data, and preferences.

    (Obs – * Such as the “Ghibli Images that were all the rage a few weeks ago.)

2 – Implement Data Protection Tools:

  • User Privacy Enhancing Technologies (PETs): Employ tools like Fawkes, which adds subtle alterations to your images to prevent unauthorized facial recognition.
  • Apply Adversarial Masks: Utilize technologies that generate adversarial identity masks to encrypt facial features, making them unrecognizable to AI models.

3 – Control Data Sharing:

  • Limit the amount of personal information you share online with AI applications.
  • Regularly review and adjust privacy se6ttings on social media and other platforms.

4 – Stay Informed About AI Developments:

  • Keep abreast of new AI technologies and their implications for privacy
  • Engage with communities and forums that discuss AI ethics for data protection

5 – Advocate for Stronger Privacy Regulations

Support Pro-Privacy Legislation: Back laws like the EU’s GDPR, California’s CCPA, or the proposed American Data Privacy Protection Act (ADPPA) that restrict excessive data collection and ensure transparency and accountability in AI usage.

Demand Algorithmic Transparency: Push for AI developers to disclose how decisions are made, especially when AI is used in sensitive areas like hiring, policing, or healthcare.

Push for “Right to Explanation”: Lobby for your right to understand how an algorithm made a decision that affects you—especially if it’s used to deny loans, filter content, or shape recommendations.

Call for Auditable AI Systems: Encourage open audits and third-party accountability of large models to detect bias, manipulation, or misuse of personal data.

Empower Data Portability and Deletion Rights: Insist on the ability to delete, move, or refuse data sharing—especially in generative AI that trains on user input.

6 – Obfuscate with “Chaff”

  • Misinformation as Defense: Intentionally insert noise into your data trail—like fake interests or searches—to disrupt behavioral profiling models. (Use with care: some systems penalize inconsistency.)

7 – Use Decentralized Tools

  • Decentralized Networks: Prefer platforms that don’t rely on centralized servers for your data (e.g., Mastodon instead of X/Twitter).
  • Self-Hosting: Where possible, use local models or self-hosted tools that don’t report back to corporate servers.

8 – Build Ethical Awareness

  • Demand Consent-Based AI: Advocate for opt-in models where AI systems only learn from you with explicit permission—no more “silent training.”
  • Teach Others: Help friends and communities understand how their data may be used or exploited. Empowering others builds systemic resistance.