Is AI hijacking your intent? A formal control algorithm to measure it
I’m an independent researcher proposing State Discrepancy, a public-domain metric to quantify how much an AI system changes a user’s intent (“the Ghost”). The goal: replace vague legal and philosophical notions of “manipulation” with a concrete engineering variable. Without clear boundaries, AI faces regulatory fog, social distrust, and the risk of being rejected entirely. Algorithm 1 (on pp.16–17 of the linked white paper) formally defines the metric: 1. D = CalculateDistance(VisualState, LogicalState) 2. IF D < α : optimization (Reduce Update Rate) 3. ELSE IF α ≤ D < β : warning (Apply…
In plain words
State Discrepancy is a public-domain metric proposed by an independent researcher to quantify how much an AI system alters a user's stated intent. It provides a formal control algorithm with tiered responses—from optimization and warnings to intervention and security protocols—based on measuring distance between visual and logical states. Designed for AI developers and regulators, it aims to replace vague notions of manipulation with concrete engineering variables, reducing regulatory uncertainty and building user trust in AI systems.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I’m an independent researcher proposing State Discrepancy, a public-domain metric to quantify how much an AI system changes a user’s intent (“the Ghost”). The goal: replace vague legal and philosophical notions of “manipulation” with a concrete engineering variable. Without clear boundaries, AI faces regulatory fog, social distrust, and the risk of being rejected entirely. Algorithm 1 (on pp.16–17 of the linked white paper) formally defines the metric: 1. D = CalculateDistance(VisualState, LogicalState) 2. IF D < α : optimization (Reduce Update Rate) 3. ELSE IF α ≤ D < β : warning (Apply Visual/Haptic Modifier proportional to D) 4. ELSE IF β ≤ D < γ : intervention (Modulate Input / Synchronization) 5. ELSE : security (Execute Defensive Protocol) The full paper is available on Zenodo: https://doi.org/10.5281/zenodo.18206943
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
