Timnit Gebru

@timnitGebru

Exactly what I said in an interview a couple of days ago (along with references for sound evaluation of so-called “reasoning” showing how results collapse after simple changes to the eval data. But in times of scientific illiteracy & media stenography this is what happens.
打开原帖#511482
  1. Industry

    Databricks: Genie Ontology works on day one, but the quality of its answers impro…
  2. Industry

    Cohere: Parse 5 offers the best price for commonly-formatted enterprise docum…
  3. Industry

    OpenAI Developers: We’ve fixed a bug that was degrading image understanding in GPT-6 Sol…