causal
Agents fail on reliability not context length
AI agents haven't taken off primarily because of insufficient 'nines of reliability'—if you chain tasks each with only 90% success the compound probability collapses, but if base success were 99% chaining wouldn't be a problem; long context is necessary but not the limiting factor, so agents may follow a step function as model scale adds the extra reliability nine.
causalpending
Speaker
Sholto DouglasEvidence Quote
“I think that's more aboutnines of reliabilityand the model actually successfully doing things. If you can't chain tasks successively with high enough probability, then you won't get something that looks like an agent.”
Created: 6/13/2026, 3:31:11 AM
Your notes
Loading notes...