• Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    AI
    Report

    Cross-task improvement reportedly not shown in five of seven reviewed robot evaluation protocols

    A post describing the paper says its six levels range from no autonomous improvement to independently verified recursive gain.

    2 Sources, 2h ago, first seen 2h ago

    TLDR

    A post describing “Who Improves the Robot? Toward Physical Recursive Self-Improvement” says five of seven robot evaluation protocols examined did not show improvement across tasks. The post says robots still depend on people to collect data, diagnose failures and choose which updates to keep. It also says the paper’s map of systems from 2022 to 2026 has no confirmed L5 case, the level for independently verified recursive gain.

    Combined views

    —

    2 Sources, first seen 2h ago

    — likes— comments— saves— reposts

    Combined views

    —

    2 Sources, first seen 2h ago

    — likes— comments— saves— reposts
    Image: @rohanpaul_ai on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 Sources

    Rohan Paul@rohanpaul_aiVery insightful survey paper from, written by many of the top labs including MIT, Stanford, Google, Microsoft, for Physical Recursive Self-Improvement Robots still rely on people to collect data, diagnose failures, and choose which updates to keep. Argues that 5 of 7 robot self-improvement studies they checked never showed gains on a different task. Self-improvement claims need tests on tasks that require different skill sequences, and finds most reviewed protocols lack them. Humans still collect their data, diagnose failures, and pick which updates to keep. Real trials are slow, noisy, costly, and sometimes irreversible, so digital self-improvement methods need rethinking. They define 6 levels, from L0 with no autonomous improvement to L5 with independently verified recursive gain. The middle levels separate updates to skills from updates to the improvement method, on 1 task or across tasks. Their map of systems from 2022 to 2026 has no confirmed L5 case. Of 7 robot evaluation protocols they examined, 5 did not show improvement across tasks.2h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Rohan Paul@rohanpaul_aiVery insightful survey paper from, written by many of the top labs including MIT, Stanford, Google, Microsoft, for Physical Recursive Self-Improvement Robots still rely on people to collect data, diagnose failures, and choose which updates to keep. Argues that 5 of 7 robot self-improvement studies they checked never showed gains on a different task. Self-improvement claims need tests on tasks that require different skill sequences, and finds most reviewed protocols lack them. Humans still collect their data, diagnose failures, and pick which updates to keep. Real trials are slow, noisy, costly, and sometimes irreversible, so digital self-improvement methods need rethinking. They define 6 levels, from L0 with no autonomous improvement to L5 with independently verified recursive gain. The middle levels separate updates to skills from updates to the improvement method, on 1 task or across tasks. Their map of systems from 2022 to 2026 has no confirmed L5 case. Of 7 robot evaluation protocols they examined, 5 did not show improvement across tasks.2h
    Today's Rank

    #9

    Today's Rank

    #9