NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#lego

1 stories this week · 3 this month · 3 in 6 months · mostly AI

Stories per day · 30 days

Relatedagents2 benchmark2 brickagent2 brickbench2 agentic-coding1 brickwright1 design1 embodied-design1 generative-ai1 hobby1 open-source1 physical-feasibility1 show-hn1 text-to-3d1

3 stories, newest first · one card per story

Hugging Face daily papers4d ago

BrickWright guides agents to physically feasible LEGO brick builds

On 512 prompts, guided agents reach 100% validity versus 9% to 69% for unguided baselines, the authors report.

brickwright agentic-coding

1

arXiv cs.AI / cs.LG / cs.CL17d ago

BrickBench: Evaluating Agentic Brick Design

BrickBench scores agents on designing physically buildable LEGO assemblies from a discrete parts library.

benchmark agents

1

Hugging Face daily papers18d ago

BrickBench: Evaluating Agentic Brick Design

BrickBench scores coding agents on designing text-conditioned LEGO sets that can actually be built.

benchmark agents

3