Claims › Epistemic self-classification › C011
C011
From the research log · What Counts as Introspection ¶10 · ¶10 · assumed
…Alongside this, the reportable component of a concept’s representation turns out to carry a median of six to seven per cent of that representation’s variance, with the rest sitting outside it.
“What a model can say about its own processing is a narrow and selective channel onto that processing, not a transcript of it.”
Lindsey’s own numbers point the same way from a different angle: introspective detection succeeds on a minority of trials even in the strongest models he tested, and models asked to describe the mechanics behind their own calculations often describe them wrongly.…
What a model reports about its own workings is not a log of them. The reportable part of a representation carries a small share of its variance, and the same information can drive the task while bypassing that part entirely, which is why a protocol cannot ask the model to certify its own output.
The five layers, for this claim
The same core in the infographic, with the claims it touches.
Relations
- confirms → C010 The premise the whole framework rests on, in its narrow form: a model may represent that a passage is in Spanish, or that it is being evaluated, without representing that the assertion it is about to make is causal rather than correlational. A channel this narrow is not one a protocol can route the typing of a claim through.
Notation
- Claim typeWhat kind of statement it is, so that the right test can be applied. Proposed until checked by hand.
- D1.2 · empirical-quantitative
- FunctionWhat a claim does for the programme: a conceptual tool, a working method, corrective evidence, a technical reference.
- corrective datum
- StanceHow the programme holds the claim: assumed, used, or contested.
- assumed
- Cite this
- claudiocammarano.com/en/claims/c011/