flâneur

Vineeth Veligeti

0 followers · 5 following · 272 views

on the atlas — 3

highlights — 7

  • We examine several variants of the Jacobian lens methodology (e.g. computing only present and not future token effects, freezing attention patterns while computing Jacobians, and varying the number of contexts over which we average) in §A.7; our qualitative results are robust to these choices.
    Verbalizable Representations Form a Global Workspace in Language Models
  • It also demonstrates a new general-purpose training technique for shaping a model’s internal thoughts, and consequently its behaviors.
    Verbalizable Representations Form a Global Workspace in Language Models
  • by training it to articulate those principles if it were interrupted and asked to reflect (§7).
    Verbalizable Representations Form a Global Workspace in Language Models
  • For instance, it only identifies vectors associated with concepts that correspond to single tokens in the model’s vocabulary, but many important concepts correspond to multiple tokens (though see §A.9 for extensions that can capture multi-token words and phrases). We comment on these shortcomings, and proposals for addressing them, in Limitations. Nevertheless, we find that the J-lens in its current form is sufficient to uncover a great deal of important structure.
    Verbalizable Representations Form a Global Workspace in Language Models
  • A nation that possesses powerful AI facing one without it—or even facing one that is behind in AI by 3 years—could be the equivalent of an army of World War II Marines facing an army of medieval swordsmen.
    Dario Amodei — Policy on the AI Exponential
  • This could mean that a suitably-designed legal review panel or the judicial branch have their finger on an “off switch”, that the systems themselves are intrinsically trained to seek out and respond to legitimate oversight authority, or both.
    Dario Amodei — Policy on the AI Exponential
  • Starting [at a young age] he’s read everything that he could find about business. The subject that interests him, he’s read newspapers, biographies, trade press. He went over to his grandfather who was a grocer and he read the progressive grocer magazine, and he read articles on how to stock a meat department... What he’s really done is he’s created this immense vertical filing cabinet in his brain of layers and layers and layers of files of information that he can draw back on now for more than 70 years worth of data.
    Curius / Onboarding