Not satire, though I get why the terminology looks odd. The language comes from materials science because the math is the same: deterministic state updates with hard thresholds. In most AI systems, exclusion relies on probabilistic sampling (temperature, top-k, nucleus), which means you can’t replay decisions exactly. This explores whether exclusion can be implemented as a deterministic state machine instead—same input, same output, verifiable by hash.
“Mechanical” is literal here: like a beam fracturing when stress exceeds a yield point (σ > σᵧ), candidates fracture when accumulated constraint pressure crosses a threshold. No randomness, no ranking. If that framing is wrong, the easiest way to test it is to run the code or the HF Space and see whether identical parameters actually do produce identical hashes.
nextaccountic|1 month ago
Problem is, we sometimes want LLMs to be probabilistic. We want to be able to try again if the first answer was deemed unsuccessful
foobarbecue|1 month ago
Nevermark|1 month ago
> At each step, stress increments are computed from measurable terms such as alignment and proximity to a verified substrate.
Well obviously its ... uh, ...
It may not be, but the whole description reads as category error satire to me.
verhash|1 month ago
“Mechanical” is literal here: like a beam fracturing when stress exceeds a yield point (σ > σᵧ), candidates fracture when accumulated constraint pressure crosses a threshold. No randomness, no ranking. If that framing is wrong, the easiest way to test it is to run the code or the HF Space and see whether identical parameters actually do produce identical hashes.