argumentA line of reasoning from premises to a conclusion. Like a claim, it belongs to no one who makes it.constitution →

The argument from extrapolating the time-horizon trend

forThis argument, if it holds, bears in favour of the claim.constitution →By the end of 2027, AI systems will be able to complete tasks that take a skilled person weeks.

The argument

METR's 50% time horizon for frontier models on its software task suite stood at roughly 12 to 16 hours in early 2026, and the horizon has recently doubled every few months. Those hours are read from METR's human baseline times, taken as a fair measure of task length. Continuing that growth for the 21 months to the end of 2027 gives horizons of roughly a hundred to several hundred hours, past a working week. The argument also needs two further premises: that the trend does not break before 2027 ends, and that 50% success on METR-style software tasks counts as being able to complete tasks that take a skilled person weeks.

Does it work?

Does it follow?: likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
Do the premises hold?: 1 doubtful1 not separately assessed

Granting its premises, the conclusion follows with room to spare: even a seven-month doubling reaches multi-week horizons before the end of 2027. The weight falls on the recent doubling time, on the human-time scale, which is doubtful for the longest tasks because most of their times are estimates, and on two unstated premises: that the trend does not break, and that the benchmark speaks to weeks-long work beyond precisely specified software tasks. An inflated time scale combined with a slower true doubling could leave the end-2027 horizon near one working week, so the baseline doubt trims the margin; the external-validity premise remains the weaker link.

Premises

UnassessedNo current assessment. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.constitution →Doubling time, in days, of the 50%-task-completion horizon of frontier AI models released from 2024 onward on METR's software task suite
DoubtfulThe evidence weighs against the claim, but the examination is incomplete or the evidence is indirect.constitution →METR's human baseline times reliably measure the length of its software tasks.

Where it is made

Passages where sources make, criticize or mention this argument. They record where it appears, not how strong it is, and none has precedence over another.

When AI builds itselfmakes itleaves a premise unstatedThe passage relies on a premise the inference needs without saying it.constitution →
In March 2024, Claude Opus 3 could complete software tasks that take humans about four minutes to complete. A year later, Claude Sonnet 3.7 managed tasks that took about an hour and a half. A year after that, Claude Opus 4.6 managed 12-hour tasks.

Earlier ratings

Nov 14, 2026likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
Granting that the trend continues and that 50% success on METR-style software tasks counts as being able to do such tasks, the conclusion follows with room to spare: even a seven-month doubling reaches multi-week horizons before the end of 2027. The weight falls on the recent doubling time and on two unstated premises: that the trend does not break, and that the benchmark speaks to weeks-long work beyond precisely specified software tasks. The second premise is the weaker link.