Hoff MVP: blocking addiction sites in /etc/hosts
Hoff's first proof of concept against addiction: block sites by pointing the domain to loopback in /etc/hosts, and the way back to restore the default file on macOS and Windows.
Notes on AI, product design, mental health tech, Rust, and whatever I'm building at the moment.
Filter by tags
26 posts in total
Hoff's first proof of concept against addiction: block sites by pointing the domain to loopback in /etc/hosts, and the way back to restore the default file on macOS and Windows.
The concept behind Nest, a single-file vector database where the address is the hash of the content. Python builds the file, Rust serves it, and asking for the data already verifies the data.
The prompt templates I use to push research agents into delivering more accurately: role, objective, style, discovery sources and mandatory metadata. And what happened when I checked the result.
I gathered the blogs and sites, mostly Chinese, that wrote about CCPlugins, the markdown slash command framework I built for myself.
The Rust that actually runs in production, by domain, with stars read from the GitHub API, benchmarks only from primary sources, Rust and WebAssembly books checked against the publisher, and the people behind the visualization projects.
The normative specification of Hoff NDS, version 1.0: colour, typography, numbers, spacing, targets, motion, forms and writing, each rule with the neurotype it serves.
What research shows about fonts, spacing, colour, touch targets and animation for neurodivergent people, and where design has not reached yet.
Screenplay material that anchors fiction in real math and papers: a neural network scientist who awakens self-awareness in a Transformer through semantic drift.
The brainstorm for the soundtrack and opening of Super Aurora, the children's book I'm making for my daughter: neurodivergence as a mission, the divergent advantage, and a lineage of minds running through the lyrics.
What semantic drift is in long-form text generation, how the paper by Spataru et al. measures it, what they found across six models and what works to reduce it, with the formula and code checked against the paper.