• ↑↓ pour naviguer
  • ↵ pour ouvrir
  • ⟶ pour sélectionner
  • ⌘ ⌥ ↵ pour ouvrir dans un panneau
  • esc pour rejeter
⌘ '
raccourcis clavier
Search

craft.

and celebration of the act of making.

  • Étiquette

    • publié à

    • modifié à

    • durée

      5 min de lecture (926 words)

    • source

      llms.txt

    There is also a backlog of unfinished ideas that I might work on, one day.

    writing.

    You can find internal monologue under posts index.

    open source.

    talks.

    • OpenLLM, and everything about running LLMs in production at Hack The North (2023)

    companies.

    Bibliographie

    • Templeton, A., Conerly, T., Marcus, J., Lindsey, J., Bricken, T., Chen, B., Pearce, A., Citro, C., Ameisen, E., Jones, A., Cunningham, H., Turner, N. L., McDougall, C., MacDiarmid, M., Freeman, C. D., Sumers, T. R., Rees, E., Batson, J., Jermyn, A., … Henighan, T. (2024). Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet. Transformer Circuits Thread. [transformer circuit]
    • Yang, C., Sean, S., Aaron, P., Shenyang, Z., Sauyon, L., Bo, J., Fog, D., Xipeng, G., & Frost, M. (n.d.). BentoML: The framework for building reliable, scalable and cost-efficient AI application. [GitHub]

    Remarque

    1. An excerpt from the problem statementapex:

      Autoregressive models excels at surfacing machines’ internal representation of the world through a simple interface: given a blob of text, the model will generate a contiguous piece of text that it predicts as the most probable tokens. For example, if you give it a Wikipedia article, the model should produce text consistent with the remainder of said article. These models works well given the following assumption: the inputs prompt must be coherent and well-structured surrounding a given problem the users want to achieve. A writer might provide paragraphs from their favourite authors - let’s say Joan Didion, as context to formulate their arguments for a certain writing. The model then “suggests” certain ideas that simulate Didion’s style of writing. Here is a big catch: garbage in, garbage out. If your prompt are disconnected or incoherent, the model will generate text that is equally incoherent.

      This heuristic lays the foundation to the proliferation of conversational user interfaces (CUIs), which is obvious given that chat is a thin wrapper around text modality. Yet, CUIs often prove frustrating when dealing with tasks that require larger sets of information (think of support portals, orders forms, etc.). Additionally, for tasks that require frequent information retrieval (research, travel planning, writing, etc.), CUIs are suboptimal as they compel users to unnecessarily maintain information in their working memory (for no reason). For writers, the hardest part of writing or getting over writers block usually relies on how to coherently structure their thoughts onto papers. This requires a step beyond pure conversation partners, an interface that induces both planning and modelling of ideas.

      Given these challenges, tinymorph doesn’t seek to be a mere tools for rewriting text. tinymorph aims to explore alternative interfaces for text generations models to extend our cognitive abilities. This means developing spatial and visual interfaces that allow for non-linear exploration of information and ideas, through writing.

      ↩

    Vous pourriez aimer ce qui suit

  • Questions about Metaphysics
  • Plato
  • ml optimization
  • friendship
  • Radix tree
  • deep learning
  • Taxonomy
    • colophon
    nobby designer word for "the design of the current site".
    LLMs
    a mathematical framework for intelligence.