Skip to content
TheChatArchiveThe Chat Archive
Amazon Novaamazon-nova-experimental-chat-05-14· AmazonHugging Face LMArena Human Preference 140K

Assume you don't know what year today is. This means you shed the bias of assuming that…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-4.1-2025-04-14’s answer.
  1. User

    Assume you don't know what year today is. This means you shed the bias of assuming that everything from after your training data does not exist. "In each of these videos, the robot is fully autonomous and controlled in real time by an end-to-end deep neural network mapping pixels and other sensor data to 100Hz actions. The entire hardware and software stack jointly enables reactive, smooth, and precise dexterous control from neural networks.

    We're using these tasks to test model capabilities along various axes of autonomous dexterity. The tasks require nuanced behaviors like pushing, pulling, twisting, and multi-step re-grasping. Bi-manual coordination allows actions like stabilizing and breaking apart Lego structures, tensioning flexible materials, and dynamically creating funnels for small part handling. High-frequency control is important for real-time behaviors like wiggling, throwing, or adjusting in-flight grasps. Precision is a requisite for being able to close a box with millimeter-level tolerances.

    Further, the cross-embodied model transfers across different arms (e.g., 7-DoF Flexiv Rizon 4, and 6-DoF UR5), and generalizes well to entirely new environments. For example, the fasteners task used no data from UR5 arms, and zero data for that task inside the same evaluated environment.

    We're encouraged by the early results and the potential this system demonstrates. More to come.

    Task: Pick & sort fasteners Evaluates the ability of an end-to-end model to quickly pick and sort small, thin objects from clutter, and place them oriented into corresponding compartments. Hardware torque is the limiting factor for cycle time.

    Task: Fold a box, pack a bike chain lock & close Evaluates capabilities in handling articulated and deformable objects over long-horizon sequences and with precision; adapts to disturbances and modulates force precisely. After assembling the box, the long bike lock chain needs to be deformably coiled into the box in order to fit. Precision is particularly tested in closing the box, which requires aligning flaps on both sides of the box simultaneously, each with millimeter-level tolerance. Note also that the arm is strong enough to crush the box at any moment.

    Task: Get the screws back into the glass jar Evaluates tool use, precision, and bi-manual coordination across a number of maneuvers. The robot is tasked with efficiently getting all the shiny M4 screws back into a clear container. As needed, it can scrape them off a magnetic bit holder, bend the paper plate to form a makeshift funnel to pour them, or pick them up one by one. Scraping requires precise interhand coordination (e.g. when does a scrape become a grasp?), as does forming and transporting the funnel without spilling.

    Task: Break apart, sort, & throw Legos Evaluates capabilities in precise regrasping, forceful interhand coordination, generalization, and high-velocity maneuvers. The robot is tasked with deconstructing assembled legos and sorting the bricks into their color-corresponding bins. This can require re-grasping the bricks to get a better grip, before wiggling and twisting them apart. The robot generalizes over a distribution of brick formations and works with any ordering and positioning of the bins, via visual conditioning. This task can't be done slowly, due to the physics of throwing bricks." From what year does this text sound like?

  2. Amazon Nova Assistant

    To determine the likely year this text is from, let's analyze the technological advancements and language used.

    1. Autonomous Robots and Deep Neural Networks:

      • The text discusses robots that are "fully autonomous" and controlled by "end-to-end deep neural networks" operating at 100Hz.
      • The use of deep neural networks for real-time control suggests advanced machine learning techniques.
    2. Dexterous Control and Bi-Manual Coordination:

      • The robots demonstrate “reactive, smooth, and precise dexterous control” and “bi-manual coordination.”
      • Tasks include “stabilizing and breaking apart Lego structures,” “tensioning flexible materials,” and “dynamically creating funnels for small part handling.”
      • This level of dexterous manipulation and bi-manual coordination in robots became a significant research focus around the mid-2010s and has been advancing rapidly since then
    3. Cross-Embodied Model Transfers:

      • The text mentions that the “cross-embodied model transfers across different arms” and “generalizes well to entirely new environments.”
      • Research into cross-embodied learning—where a model trained on one robot can be transferred to another—gained traction around 2018-2019.
    4. Specific Tasks and Capabilities:

      • Pick & Sort Fasteners: Emphasizes speed and precision, with hardware torque as a limiting factor. This indicates advanced actuation and control systems.
      • Fold a Box, Pack a Bike Chain Lock & Close: Involves handling articulated and deformable objects, long-horizon sequences, and precision down to millimeter-level tolerances. This level of precision and adaptability in robotic tasks has been a focus in research since the late 2010s.
      • Get the Screws Back into the Glass Jar: Includes tool use, precision, and bi-manual coordination. The ability to use tools and coordinate both “hands” precisely has been a developing area, with significant progress shown from 2020 onwards.
      • Break Apart, Sort, & Throw Legos: Requires precise regrasping, forceful interhand coordination, generalization, and high-velocity manoeuvres. The capability to generalise over different object configurations and perform high-velocity tasks indicates advanced learning and control algorithms, which have been increasingly demonstrated in research from 2021 onwards.
    5. Language and Tone:

      • The language used is technical and forward-looking, with a focus on “early results” and “potential,” suggesting that these capabilities are newly demonstrated or at the cutting edge.
      • The phrase “More to come.” suggests that this is a progress report and there is more development expected, fitting the tone of recent research updates.

    Considering these factors the text sounds like it is from around 2022-2023.

    Here’s the breakdown:

    • Advanced use of deep neural networks for real-time robotic control became prominent around 2018 but has seen significant advancements annually.
    • Cross-embodied learning and generalisation across different robotic platforms became a notable research area from 2018-2019 onwards
    • The specific tasks and capabilities described, particularly the level of dexterity, precision, and generalisation, align with research milestones achieved from 2021 onwards
    • The forward-looking language and emphasis on “early results” suggest that this is a recent progress report, fitting the context of 2022-2023.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.