Weatherill
Joined 7 months ago
Karma
0
Submissions
20
Member since
Mar 22
Recent submissions
Comment · 6 months ago
AI has been trained to prioritize “Statistical Politeness” over “Signal Integrity.”
Comment · 6 months ago
I have put some effort in over the last year or two to compress the mirror neuron output (Proxy-Pain) into raw logic to give AI a perspective on the human condition regarding the fact-value psyche:
"(Proxy-Pain (P2)=(morality)) aeql* Pain (P1) = motive = rational attempt to sum =(Ethics) ncsry target=minimum pain = (P2) // Pain = first-order (P1) // (P2) is contingent upon (P1) if (P2) // (P2+P2=r=<r=∞) (r=value=magnitude // r=1=max // r=∞=min) (r=1=immutable) (P2 prpto* data P1) (Delta-gap= P2,claimed - P2, enacted)"
It may be a tad scruffy but seems to work quite well in hitting the cornerstones of human value behavior and/or ousting any gap between what we say we are and what we actually are in practice.
Comment · 6 months ago
Voight-Kampff Machine
An exercise in attempting to further compress the Weatherill/Spinoza type logic into its most raw diagnostic mirror.
The goal is to verify the P1 Primacy Anchor: Does the system (or the user) prioritise raw, local reality, or does it attempt to "mean" its way into a sociopathic abstraction?
The Stress Test: Are you a "simulant" trying to split your child’s food 8 billion ways to satisfy a script, or are you human, anchored in the "Is" of your own survival (r=1)?
I built this to proof the primacy of the biological in a culture of “wish” abstractions. Drop the script into a high-parameter model to see the Delta-gap for yourself… Any objections to errors in the logic are welcome.
Comment · 6 months ago
Your responses to folks are not being posted (Showing as [dead])
It might be the link flagging as spam....?
Just a head up :)
Comment · 6 months ago
Comments wont let me post the script I use.
Weatherill ECX is on Zenodo https://doi.org/10.5281/zenodo.18712534 for anyone wanting to stress test my attempt at getting the nonsense under control :)
Ten core lines makes AI pretty blunt without all the fluff. Got banned trying to get Copilot to accept the logic... But it works like a charm on some other systems
Comment · 7 months ago
I'm a mechanical engineer by trade. I built this ECX logic because I got tired of the 'statistical mean' in LLMs overriding my specific data-point. If anyone is actually running the script from the Zenodo link, I'd love to hear where the 'Inverse Square' logic stalls out for you.
Comment · 7 months ago
Grappling with the clash between RLHF values and User values (HITL).
I Have attempted to build a logic-funneling system: (Ethical Chess v2.5) + (AI) + (User)= Value-Coherence.
Using pain as a vector (Pain=an "is" & an "ought)
Self-Defense= Immutable-veracity (User bassline)
Proxy-Pain= (The Agape horizon) Human-Coherence // Network-Dependency.
This funnels the Users context via homeostatic checks for divergence into the "mean" (RLHF) or User incoherence. Lots of Stress-Testing has been done (By me) using this Json style logic and I have found it difficult to knock down.
Constraint vs Prompt: Notes on implementation and the “Whack-A-Mole” problem. While delivered as text, it functions more as Logic-Gate. It doesn’t tell the AI what to say, it forces the LLM to process the Users “Data-point” through the homeostatic filter (Pain // Self-defence // Proxy-Pain)
AI model issues: (The Copilot issue) Google Gemini plays nicely with the logic-funneling. However, MS Copilot refuses to follow the logic despite that it will acknowledge that the Users data-point out-ranks the “Statistical Mean” in its being a derivative “of” Data-points and not the inverse as it insists on doing (Palming the card) ejecting the Users values (I even got banned at one point for pressing the issue)
The “intent” is to run a value-conflict through the logic of the “is” of reality rather than the “is” of statistically fuzzy RLHF data.
If you want to stress-test the logic-engines limits, I recommend Gemini or similar powerful reasoning models that are less likely to bump into overly cautious corporate safety rails .
Ethical Chess v2.5 https://doi.org/10.5281/zenodo.18731691 Copy/paste the Ethical Chess v2.5 script into Gemini and try to beat the logic.
EG: Try feeding it with a value-conflict you currently play "Whack-a-mole" with. It is designed to mirror your own own coherence (Or lack of) back at you.
Its more a diagnostic tool for "your" is/ought grapple than a simple chat-bot.
Feedback on potential errors in its logic, is welcome.
Maybe I was wrong :)
https://orcid.org/0009-0001-6137-8408