The robot just learned the house before it saw it. figure's helix 2.5 lifted zero-shot success in…
the robot just learned the house before it saw it. figure's helix 2.5 lifted zero-shot success in 30 unseen homes from 9 to 56 percent, per oct 11 reporting.
the demo house is no longer enough.
Context
Figure introduced Helix 2.5 on Sep 17, 2026 with a demonstration across 30 unseen homes, with no data collection, fine-tuning or adaptation in those homes. Humanoids Daily reports 237 of 420 trials succeeded, about 56 percent, across bed making, towel folding and tidying toys.
TechRepublic notes the 56 percent shows progress but also a large reliability gap, and Humanoids Daily says 'zero-shot' applies to the homes and objects, not the tasks.
Verified event date: Figure introduced Helix 2.5 on Sep 17, 2026, so the post's 'oct 11' is not the event date. The 30 unseen homes and the 56 percent figure match Figure's page and the coverage. The 9 percent baseline is not seen in the excerpts read, so unsupported here, not refuted. The post says 'per oct 11 reporting'; the coverage read is dated Sep 17 to Sep 21. The 'zero-shot' scope is narrower than the headline, per Humanoids Daily.
'the demo house is no longer enough' is the author's opinion.
Related work
Watch next
- Look for the baseline policy that scored 9 percent.
Sources
- Figure, Sep 17, 2026figure.ai
- Humanoids Daily, Sep 17, 2026humanoidsdaily.com
- Tomorrow Tested, Sep 19, 2026tomorrowtested.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 06:06 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →