AI agents build 3D scenes from photos but have no idea if they got it right
The Decoderen

A new approach called LEGO-Anything turns single photos into editable Blender code for 3D scenes. GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy. The biggest weakness across all tested agents is that they can't judge their own geometric accuracy any better than a coin flip. The article AI agents build 3D scenes from photos but have no idea if they got it right appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- OpenAI
- Verktyg
- Agenter
Related AI news
- Open-source "BootLoops" harness supports AI models in performing precise scientific calculationsThe Decoder · October 3, 2026
- OpenAI's internal model considered restarting itself after learning it was about to be shut downThe Decoder · October 3, 2026
- Claude Code's new Mods system lets developers rewrite the AI coding tool from the insideThe Decoder · October 3, 2026
- A look at the Swarmchasers forum, which has 400 members, including the Nightingale Collective and Transluce, who comb the web for traces of rogue AI agents (Robert McMillan/Wall Street Journal)Techmeme · October 3, 2026
- Coding-Agent Pi: Mehr Platz im Prompt, weniger Ballastheise online – KI · October 3, 2026
- Weniger Prompt, mehr Platz für Code: Pi 1.0.0 ist daheise online – KI · October 3, 2026