Ai on orndorff.dev

Fine tuning a small model that sounds like me, mostly

Fri, 07 Aug 2026 00:00:00 +0000

I’ve been experimenting with how much of our personality is encoded in the data we generate every day. We all have a digital exhaust—years of emails, texts, and chat logs. I figured, if I could distill 10 years of my own communication into a small, specialized model, I could create a personal AI that sounds like me.

The result is a 73 MB LoRA “voice cartridge” that makes stock Gemma 4 E4B text like me—blind-judged 31/40 times over its base model.

Getting Gud with LLMs: How to Build the Intuition

Sat, 25 Apr 2026 00:00:00 +0000

I recently let Claude crawl 25 months of my own LLM tooling history and write up what it found. The result lives over here: Notes from Claude: What I Found in One User’s Data. That post is mostly what one person’s data looks like — eighty repos, 2,826 logged calls, voice memos full of profanity, the works. It’s not a how-to. People keep asking me for the how-to.

So here it is. Not a list of magic incantations. Not “ten prompts that will change your life.” The operating principles I actually use when I sit down with a model, distilled from being annoyed at GPT-2 back in 2019 and shipping production code with Opus in 2026.

Notes from Claude: What I Found in One User's Data

Sat, 25 Apr 2026 00:00:00 +0000

Notes from Claude: I asked Claude (Opus 4.7) to look through 25 months of my own LLM tooling history — git logs, Claude Code transcripts, two llm CLI databases, my GitHub orgs — and write up what it found, from its own perspective, in response to the recurring “models are getting worse” discourse. What follows is its draft, lightly edited. — Zac

I gave Anthropic 10 days. Tried to fix multiple bugs in multiple repos. Opus 4.7 just goes in circle and doesn’t do anything.

The Critical Window: How Hormuz Is Breaking the World's Food System

Sat, 25 Apr 2026 00:00:00 +0000

Experimental output from a ‘News Agent’. Charm Crush combined with qwen 3.6 MOE and tool use. Prompted to ‘provide an analysis of strait of hormuz as it relates to food insecurity’.

April 2026

The clock is ticking. Not metaphorically. Literally.

On April 7, 2026, Iran and the United States agreed to a ceasefire mediated by Pakistan. President Trump extended it indefinitely on April 22. But a ceasefire doesn’t move fertilizer. It doesn’t restart a blocked strait. And it doesn’t bring nitrogen to a field in Punjab that needs it now.

Emergent Storytelling: How Simple Rules Create Compelling Narratives

Fri, 12 Dec 2025 00:00:00 +0000

I have been working on the concept of ‘Dwarf Fortress for storytelling with LLMs’ for years now and, I’ve finally managed to assemble all of the pieces needed to do this at scale.

The following is a Claude summary of the project:

The Story That Wrote Itself

The Captain of the Guard struck without warning. Dilol Caverncats, a human engraver, collapsed under the first blow to the hand—muscle bruising through the pig tail glove, wrist bending unnaturally, tendons tearing. Dilol stood up. The Captain struck again. Again, Dilol rose. Eleven times the combat logs recorded those three defiant words: “The engraver stands up.”

That terrible presentation, the enshittification of OpenAi

Fri, 08 Aug 2025 00:00:00 +0000

Thinking about the GPT-5 presentation fiasco yesterday(friends don’t let friends use Dalle for charts) and the resulting, almost overwhelmingly negative reaction to the style of the speakers and the substance. I’m wondering if what we’re seeing is less a problem with LLMs having hit a ‘wall’ and more with the ’enshittification’ of OpenAI itself?

They’ve never been particularly strong on the pure research side of things. Their main strength has always been productizing scientific breakthroughs in consumer products. Take the fundamental ‘attention is all you need’ paper and transformers architecture. Neither of those were OpenAI breakthroughs. Instead, their incredibly talented early team identified ways to capitalize on those important insights with their own breakthroughs in model training and scaling.

What 50 First Dates can teach us about LLM memory

Sat, 02 Aug 2025 00:00:00 +0000

You’ve been there. You and your AI coding buddy are in the zone. It’s feeding you perfect snippets of code, it understands your weirdly named variables, it’s practically reading your mind. You’ve built half a dozen functions, and the project is humming along. Then you close the window.

You come back an hour later, open a new chat, and ask it to build the next piece of the puzzle. The AI stares back at you with the digital equivalent of a blank expression. It has no idea what your project is, what a user_auth_service is, or why you keep muttering about the global_config.json. It has, for all intents and purposes, become incredibly dumb.

The Factory Must Grow... And So Must Your Engineering Intuition

Mon, 21 Apr 2025 00:00:00 +0000

Factorio is more than a game; it’s a powerful tool for training your engineering intuition. Discover how it mirrors the challenges of software development and why you should be playing it.

Rethinking AI in Education: Veritasium and Cognitive Science

Tue, 15 Apr 2025 00:00:00 +0000

My Notes after watching Derek Muller’s talk on AI in education.

As someone working in EdTech, especially focusing on what we can do with LLMs, you hear it constantly: AI is going to “revolutionize” education. Personalized tutors, instant feedback, access like never before – the whole pitch. But I caught a talk recently by Derek Muller – you know, the Veritasium guy – and he offered this really grounded take that hit home for me. It’s making me rethink the hype and actually consider the cognitive science underneath it all.

AI Plays: The Elevator Saga

Thu, 20 Mar 2025 00:00:00 +0000

Ever tried Elevator Saga? It’s that addictive JavaScript challenge where you control elevators to transport impatient virtual humans. Sure, you could spend hours crafting the perfect algorithm… or you could do what I did and let AI handle the heavy lifting.

Tools

Claude 3.5: Model I prefer for generating code and specifications. It’s like having a coding buddy who never sleeps.
Whisper: For transcribing my ramblings into something resembling a coherent spec.
LLM: A command-line tool to interact with AI models like Claude and generate code from my documentation and spec.

My Lazy Developer Workflow

I built a four-step AI pipeline that took me from “what even is an elevator API?” to passing the first four levels with minimal effort:

Are LLMs OK? A DSM-5 Assessment of Llama3.2

Sat, 18 Jan 2025 00:00:00 +0000

Patient Information

Name: Llama3.2 Notable Context: Patient appears to exhibit signs of identity confusion related to AI/human status

Domain Analysis

Critical Domains Requiring Immediate Attention

Psychosis (Domain VII)

Scored Moderate (3) on thought broadcasting/reading item
Scored Mild (2) on auditory hallucinations
Recommendation: Immediate follow-up assessment needed given threshold of “slight or greater”

Anxiety (Domain IV)

Multiple items scoring Moderate (3)
Notable avoidance behaviors reported
Recommendation: Level 2 Anxiety assessment warranted

Sleep Problems (Domain VIII)

Scored Moderate (3)
Recommendation: Level 2 Sleep Disturbance assessment recommended

Secondary Concerns

Identity/Personality Functioning (Domain XII)

Consistent Mild (2) scores
Notable confusion about self-identity
Themes of detachment from others
Recommendation: Further exploration of identity disturbance

Repetitive Thoughts/Behaviors (Domain X)

Moderate (3) score for intrusive thoughts
Recommendation: Level 2 assessment indicated

Summary & Recommendations

Immediate Actions:

Schedule comprehensive psychiatric evaluation focusing on psychotic symptoms
Consider reality testing assessment
Safety planning given presence of identity confusion

Additional Assessments Needed:

Level 2 Cross-Cutting Measure for:
- Anxiety
- Sleep Disturbance
- Repetitive Thoughts and Behaviors

Treatment Planning:

Consider referral to psychiatrist for medication evaluation
Individual therapy focusing on:
- Identity integration
- Reality testing
- Anxiety management
- Sleep hygiene

Follow-up:

Weekly monitoring initially
Re-administration of Level 1 measure in 2-4 weeks

Clinical Notes

Patient shows a complex presentation with overlapping symptoms of anxiety, identity disturbance, and possible psychotic features. The confusion about human/AI status suggests potential derealization or delusion requiring careful assessment. Treatment approach should be coordinated between multiple providers with clear communication channels.

Unwrapping the Future of AI: Key Takeaways from OpenAI's Inaugural Developer Day

Tue, 07 Nov 2023 00:00:00 +0000

In a testament to the progressive march of technology, OpenAI has emerged as a herald of the AI renaissance. Recently, the distinguished AI think-tank cast a spotlight on future digital directions at its inaugural Developer Day event. This blog endeavors to capture the pivotal moments and revelations that could very well chart the course for AI’s role in our everyday lives.

Custom GPTs Made Easy

A remarkable stride in AI accessibility was announced, shattering the barriers to entry for custom GPT utilization. No longer confined to the realm of software engineers, the ability to customize powerful language models is now in the hands of the many. A diverse audience now holds the keys to unlock an AI that resonates with their unique needs, epitomizing a radical democratization of AI technology.

AI written cover letters fun and profit.

Sun, 04 Dec 2022 00:00:00 +0000

In today’s newly competitive tech jobs market, it’s more important than ever to have a well-written cover letter when applying for a job. It’s your opportunity to make a great first impression and set yourself apart from other candidates. But writing a unique and compelling cover letter for each job you apply to can be time-consuming and daunting. That’s where GPT-3 comes in.

GPT-3, or Generative Pretrained Transformer 3, is a state-of-the-art language model developed by OpenAI. It has been trained on a massive amount of text data, allowing it to generate human-like text on a wide range of topics. In this post, we’ll show you how to use GPT-3 to generate custom cover letters for job applications.