Re:Research acceleration: The view inside OpenAI
by ajkjk on Sunday September 06, 2026 @08:01PM
(#49592236)
that's not really how eigenvalues work... they specifically also model the case where the result keeps changing exponentially.
[ Parent
| on HN ]
Re:Research acceleration: The view inside OpenAI
by mjburgess on Sunday September 06, 2026 @08:35PM
(#49592436)
The claim is that the RSI operation is just finding a fixed point of improvement,
RSI(LLM) = RSI(LLM) -- for an optimal LLM* which is a fixed point of RSI
As for eigenvalues/vectors, they're fixed points of (1/val)A or A*val
Re:Research acceleration: The view inside OpenAI
by ekidd on Sunday September 06, 2026 @10:26PM
(#49593149)
Eigenvectors represent fixed directions, not fixed magnitudes. From Wikipedia:
> More precisely, an eigenvector v of a linear transformation T is scaled by a constant factor lambda when the linear transformation is applied to it: Tv = lambda v .
In other words, repeated multiplication of an eigenvector by a matrix can still create exponential growth.