Wu: AI autonomous task duration grew from 10 seconds to 18 hours
Scott Wu · How AI Agents Are Creating 12X Productivity Gains · Joe Lonsdale · Mar 27, 2026 · at 44:54
Scott Wu is the co-founder of Cognition (creator of Devin). He discusses model benchmark progression measured by METR with host Joe Lonsdale.
“One of the stats that people talk about a lot is this METR report, which basically says for each different model that comes out roughly how much human work can it do in an automated fashion before you have to go interrupt it and say, oh, that was wrong. Let's go do this. Right. And so it's like, you know, just two or three years ago, the answer was like 10 seconds or something. You know, you would have it write one line and then it's like, all right, the next line is already wrong. Let's stop here. Right. And at this point, it's already gotten to the point where it's in the scale of, you know, 10:20 hours. Is what the latest one has been. I think Opus 4.6, for example, I think was around 18 hours.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →