RSS

Archety­pal Trans­fer Learn­ing

TagLast edit: 5 Jul 2023 22:54 UTC by MiguelDev

Archetypal Transfer Learning (ATL) is a proposal by @whitehatStoic for what is argued by the author to be a fine tuning approach that “uses archetypal data” to “embed Synthetic Archetypes”. These Synthetic Archetypes are derived from patterns that models assimilate from archetypal data, such as artificial stories. The method yielded a shutdown activation rate of 57.33% in the GPT-2-XL model after fine-tuning.

Related Tags: Corrigibility, Inner Alignment, Outer Alignment

Ex­plor­ing Func­tional De­ci­sion The­ory (FDT) and a mod­ified ver­sion (ModFDT)

MiguelDev5 Jul 2023 14:06 UTC
8 points
11 comments15 min readLW link

Rele­vance of ‘Harm­ful In­tel­li­gence’ Data in Train­ing Datasets (We­bText vs. Pile)

MiguelDev12 Oct 2023 12:08 UTC
12 points
0 comments9 min readLW link

GPT-2 XL’s ca­pac­ity for co­her­ence and on­tol­ogy clustering

MiguelDev30 Oct 2023 9:24 UTC
6 points
2 comments41 min readLW link

A Mul­tidis­ci­plinary Ap­proach to Align­ment (MATA) and Archety­pal Trans­fer Learn­ing (ATL)

MiguelDev19 Jun 2023 2:32 UTC
4 points
2 comments7 min readLW link

On Ilya Sutskever’s “A The­ory of Un­su­per­vised Learn­ing”

MiguelDev26 Aug 2023 5:34 UTC
5 points
0 comments19 min readLW link

Re­search pro­posal: Lev­er­ag­ing Jun­gian archetypes to cre­ate val­ues-based models

MiguelDev5 Mar 2023 17:39 UTC
5 points
2 comments2 min readLW link

Archety­pal Trans­fer Learn­ing: a Pro­posed Align­ment Solu­tion that solves the In­ner & Outer Align­ment Prob­lem while adding Cor­rigible Traits to GPT-2-medium

MiguelDev26 Apr 2023 1:37 UTC
14 points
5 comments10 min readLW link