Wes Roth on Model Benchmarks and AI News

Wes Roth15m 48s
Wes Roth beside the words Test the Models.
0 comments · 0 votesOpen discussionClose discussion
Sign in to join the discussion

    Wes Roth discusses contemporary reporting about AI company financing, framing public-market prospects and their implications as uncertain.

    He demonstrates a developing economic simulation used to compare models, describing a fairness issue he says he corrected and emphasizing that the benchmark is still in progress.

    He discusses coding and ARC-AGI evaluation, including the limits of scores and test designEvaluation is the systematic assessment of a system's behaviour or results against explicit criteria.. He labels speculation about a future OpenAI model as unconfirmed.

    Original YouTube thumbnailWatch on YouTube

    Video topic coverage

    • Agents & workflows0
    • Coding & tools48
    • Models & learning84.7
    • Infrastructure & compute0
    • Research & evaluation100
    • Safety & security0
    • Business & productivity61.2
    • Creative & media0
    • Robotics & perception0
    • Society & policy23.5

    Share this video

    Wes Roth beside the words Test the Models. With WWW.ARTIFICIAL-INTELLIGENCE.VIDEO, 2 June 2026 and duration 15m 48s.

    Wes Roth discusses model evaluation and demonstrates an AI-built economic simulation.