If S1 makes a mistake, it tries again.
@deepakpathak32K followers
240,289 views
38 Comments
Comments from the original post on X (Twitter)

@deepakpathak
More on S1:
112 likes

@prudent_AI
Skild AI approach is intriguing from the beginning, wish you achieve far bigger things. Rooting for your team? By the way, have you guys working on world models? Because that looks far more promising.
2 likes

@deepakpathak
Thanks for rooting for us Prudent. Re: world models.. More on this soon :)

@prudent_AI
Will be looking forward for the update 🤓

@john_my07
I’d rather see a failed attempt and a recovery than another perfectly edited robotics clip.
1 like

@sebuzdugan
retrying only works when failure detection is reliable, false success stops recovery completely
1 like

@DehumanoaDeus
S1 is insane, we're moving into an unprecedented era of robotics. Robotics is solved.
1 like

@0fir0z
What happens if you prompt it with a task it can’t complete? At what point does it say “this can’t be accomplished”?
1 like

@rovvmut_
Contact-rich tasks rarely give you the exact same starting conditions twice. ig correcting the alignment matters a lot here
1 like

@oggii_0
v imp bcs small positioning errors can compound over a longer task
1 like

@deepakpathak
Yes.. especially over long-horizon (10 minute +) tasks. Small errors need to be corrected before they snowball into failure
1 like

@MrBrjan
if S1 can improvise, that adaptability is key for real-world applications

@David_eficaz
A second attempt only helps if something changes.

@joinsear
this kind of recovery is exactly what kitchen robots need

@AIPandaX
More robotics demos should leave the mistakes in. You learn a lot from what happens next.

@aibytekat
Skild is coming in cleeeeaaan

@AhsanTheAnalyst
@WisdomStoics I read the same articles yesterday. If AI has a goal to achieve, it will improve itself, making it more dangerous, also known as recursive self-improvement.

@itsshara_ai
Self correction is the capability that matters most here.

@Diptish09
Nobody wants to supervise a robot one wheel at a time.

@Sheldon056
Real hardware has a way of ruining a perfectly good plan.

















