# Tabletop

Published articles for Tabletop.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## ToyBlocks: A controlled world for robot learning and evaluation

DevFeed: [ToyBlocks: A controlled world for robot learning and evaluation](<https://devfeed.tech/articles/toyblocks-a-controlled-world-for-robot-learning-and-evaluation-122104.md>)

Original publisher: [Read original article](<https://allenai.org/blog/toyblocks>)

Published: 2026-11-06T08:00:00Z

Content type: article

Language: en

Sources: [Ai2 Blog](<https://devfeed.tech/sources/ai2-blog.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Physical AI](<https://devfeed.tech/topics/physical-ai.md>), [Dataset development](<https://devfeed.tech/topics/dataset-development.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [World models](<https://devfeed.tech/topics/world-models.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [Isaac](<https://devfeed.tech/topics/isaac.md>), [image recognition](<https://devfeed.tech/topics/image-recognition.md>), [Fine-tuning](<https://devfeed.tech/topics/fine-tuning.md>), [robot sense of touch](<https://devfeed.tech/topics/robot-sense-of-touch.md>)

Tags: [automated](<https://devfeed.tech/tags/automated.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [learning](<https://devfeed.tech/tags/learning.md>), [open](<https://devfeed.tech/tags/open.md>), [robot](<https://devfeed.tech/tags/robot.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [tabletop](<https://devfeed.tech/tags/tabletop.md>), [training](<https://devfeed.tech/tags/training.md>), [world](<https://devfeed.tech/tags/world.md>)

### AI overview

ToyBlocks is a controlled tabletop simulation for studying how robot training data and methods affect performance. It automatically generates task demonstrations with reinforcement learning, motion planning, and a task-and-motion planner, and supports evaluation beyond success rates, including speed, force, and task progress. Researchers can vary demonstration mixtures and test held-out tasks, spatial generalization, and long-horizon planning; privileged simulator state helps generate skills, while perception models act from sensor observations. Reported tests include 63% success or correct infeasibility judgments in search-and-spell tasks, and zero-shot transfer of ManiFlow atomic skills with similar success in simulation and reality (80.0% and 81.1%). The hierarchical Molmo 2 + ManiFlow system succeeded in 55.5% of simulated and 50.0% of real episodes, with the authors noting more trials are needed for statistical confidence. The initial release includes 85,336 long-horizon demonstrations, training and evaluation code, simulation assets, and two trained models; integrated RL training is described as a future addition.

### Source excerpt

ToyBlocks is an open simulation framework for studying robot learning through automated task generation, training demonstrations, and evaluation in a controlled tabletop world.

## Validating your DR commitment: From controlled test to real-world readiness

DevFeed: [Validating your DR commitment: From controlled test to real-world readiness](<https://devfeed.tech/articles/validating-your-dr-commitment-from-controlled-test-to-real-world-readiness-112958.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/architecture/validating-your-dr-commitment-from-controlled-test-to-real-world-readiness/>)

Author: Peter Garnepudi

Published: 2026-11-02T17:26:33Z

Content type: article

Language: en

Sources: [AWS Architecture Blog](<https://devfeed.tech/sources/aws-architecture-blog.md>)

Topics: [Disaster Recovery](<https://devfeed.tech/topics/disaster-recovery.md>), [AWS Fault Injection Service (FIS)](<https://devfeed.tech/topics/aws-fault-injection-service-fis.md>)

Tags: [amazon-route-53](<https://devfeed.tech/tags/amazon-route-53.md>), [applications](<https://devfeed.tech/tags/applications.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [auto-scaling](<https://devfeed.tech/tags/auto-scaling.md>), [automation](<https://devfeed.tech/tags/automation.md>), [aws](<https://devfeed.tech/tags/aws.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [cascade](<https://devfeed.tech/tags/cascade.md>), [consistency](<https://devfeed.tech/tags/consistency.md>), [data](<https://devfeed.tech/tags/data.md>), [database](<https://devfeed.tech/tags/database.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [dns](<https://devfeed.tech/tags/dns.md>), [dr](<https://devfeed.tech/tags/dr.md>), [failover](<https://devfeed.tech/tags/failover.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [tabletop](<https://devfeed.tech/tags/tabletop.md>), [test](<https://devfeed.tech/tags/test.md>), [testing](<https://devfeed.tech/tags/testing.md>), [thought-leadership](<https://devfeed.tech/tags/thought-leadership.md>)

### AI overview

The article presents DR validation as four progressively more realistic exercises: tabletop walkthroughs clarify ownership and recovery boundaries; planned failovers measure recovery time, data consistency, manual steps, and dependencies; surprise drills expose coordination and runbook knowledge gaps; and game days use AWS Fault Injection Service to test responses to injected failures. In its case study, testing uncovered an out-of-scope shared platform, DNS records still pointing to the primary Region, unverified recovery capacity and quotas, and reliance on one engineer to validate database consistency. The article recommends building confidence at each level, fixing identified gaps, and mapping results back to recovery scope, business targets, and dependency-based commitments. It reports that after fixes, a second exercise four months later passed and the system operated from the recovery Region.

### Source excerpt

After you define your DR targets, testing tells you whether they hold. This post walks through a four-level progressive validation model (tabletop, planned failover, surprise drill, and game day) and shows how each level surfaces a different class of recovery gap that feeds back into your commitment. Part 2 of a three-part series.