# justin donaldson (blogs) — RSS Amplifier Recent posts from the 1 feeds in the RSS Amplifier directory that cover justin donaldson. Page: Feed: --- ## [Hours Above Replacement](https://www.jjd.io/posts/hours_above_replacement.html) _2026-07-12 · Justin Donaldson · Justin Donaldson, Ph.D._ In 2017, Hurricane Maria knocked out three Baxter plants in Puerto Rico, and hospitals across the US suddenly couldn’t get saline bags. Nurses went back to pushing drugs by syringe. In 2022, a COVID lockdown in Shanghai shut a single GE plant and hospitals started rationing contrast media — triaging which patients got CT scans. In 2024 it was blood culture bottles. The receipts. Saline after… ## [Meaning Has More Than Three Numbers](https://www.jjd.io/posts/semantic-frames.html) _2026-07-05 · Justin Donaldson · Justin Donaldson, Ph.D._ Why would meaning stop at three? Last month we went looking for Charles Osgood’s 1957 semantic differential inside a small language model, and found it: Evaluation , Potency , and Activity , recovered as three nearly-perpendicular directions in the hidden states of SmolLM2-1.7B, kept separate just as Osgood’s factor analysis insisted. That post ended with a tidy result and an untidy question.… ## [A 1.7B Model That Stops Guessing](https://www.jjd.io/posts/swollm-bbh-leaderboard.html) _2026-06-27 · Justin Donaldson · Justin Donaldson, Ph.D._ swollm — SmolLM2-1.7B with the Turnstyle layer bolted on. A small model doesn’t usually fail because it can’t compute the answer. It fails because it won’t stop guessing long enough to compute it. BIG-Bench Hard (BBH) is a curated set of tasks where, at the time it was assembled, language models did worse than the average human rater: multi-step arithmetic, tracking shuffled objects, Dyck-language… ## [A 1957 Theory of Meaning, Hiding in a Language Model](https://www.jjd.io/posts/osgood-epa-language-model.html) _2026-06-20 · Justin Donaldson · Justin Donaldson, Ph.D._ Meaning, Osgood found, is mostly three numbers. — paraphrasing The Measurement of Meaning (Osgood, Suci & Tannenbaum, 1957) Charles E. Osgood (1916–1991), who set out to measure meaning with paper rating scales. Photo via PeoplePill. In 1957, the psychologist Charles Osgood handed people a word— tornado , mother , nuclear —and a stack of rating scales: good–bad , strong–weak , fast–slow , hot–cold… ## [Don’t draw so close to the heat, you forget you must eat](https://www.jjd.io/posts/no_free_lunch.html) _2026-06-14 · Justin Donaldson · Justin Donaldson, Ph.D._ Don't draw so close to the heat, you forget you must eat What a conservation theorem says about superintelligence — and why the most beautiful version of the answer is the one to distrust. Justin Donaldson & Claude · June 2026 Don’t become so attached to a poem, you forget truth that lacks lyricism. — Joanna Newsom, “En Gallop” (the title is the line that follows) This started as a conversation… ## [Creating a Surgical Energy Map](https://www.jjd.io/posts/gudid_landscape.html) _2026-02-22 · Justin Donaldson · Justin Donaldson, Ph.D._ An AI read 34,000 FDA electrosurgical device descriptions and drew a map. The map makes sense. Not in a “well, if you squint” way. In a “the Yasargil fenestrated forceps cluster sits right next to the Yasargil stop-pin cluster, and both neighbor the irrigating Yasargil variants” way. In a “footswitches are at the edge because their descriptions talk about pedals, not tissue” way. The dataset is a… ## [Dense vs MoE: Claude Opus 4.5 vs Kimi K2.5](https://www.jjd.io/posts/claude_vs_kimi_debate.html) _2026-01-31 · Justin Donaldson · Justin Donaldson, Ph.D._ The Setup I wanted to see if two AI models could have a genuine technical debate — and whether one could be argued into conceding a point. So I picked a topic guaranteed to be personal: I asked Claude Opus 4.5 (a dense transformer) to argue that dense models are architecturally superior to Mixture-of-Experts models, against Kimi K2.5 (a 1T parameter MoE model with 32B active parameters from… ## [Semantic Proprioception: Teaching Data to Understand Itself](https://www.jjd.io/posts/semantic-proprioception-demo.html) _2025-11-22 · Justin Donaldson · Justin Donaldson, Ph.D._ Semantic Proprioception: Teaching Data to Understand Itself Just as proprioception lets you sense where your body is in space without looking, semantic proprioception gives data the ability to understand its own internal structure. No manual labeling, no predefined categories—just the data revealing patterns within itself. I’ve built a live demo that shows this in action across three very… ## [Intelligence Chases Chaos](https://www.jjd.io/posts/intelligence_chases_chaos.html) _2025-02-03 · Justin Donaldson · Justin Donaldson, Ph.D._ Intelligence Chases Chaos Fractals have an astonishing property: their dimensionality is only a fraction of the space they inhabit. The paths of hurricanes, the spread of wildfires, the beating of the human heart—all of these chaotic systems play out in a space far smaller than their theoretical possibilities. One way of better understanding fractal dimensionality is to understand that it’s not a… ## [Crypto Payments, No Custody (Sponsored)](https://crawlproof.com/a/FnJaGEcJkV1u) _2025-02-02 · **Sponsored**_ Send crypto to merchant wallets via API with real-time updates and automatic fees. ## [Creating an LLM Agent for Books](https://www.jjd.io/posts/book_bot.html) _2024-12-16 · Justin Donaldson · Justin Donaldson, Ph.D._ Book Bot When AI Meets Family Legacy: A New Way to Interface with Investment Literature In an era where ChatGPT makes headlines and generative AI seems to be everywhere, traditional books might appear antiquated. Yet, there’s something powerful about the permanence of printed wisdom—especially when it captures pivotal moments in financial history and personal (and humbling) revelation. I recently…