This work was done while at METR. Introduction GDM recently released a paper (Emmons et al.) showing that, contrary to previous results, the chain-of-thought (CoT) of language models is more faithful when the model’s CoT is necessary for it to complete a task. They examine three settings where an actor...
Summary METR blogpost | X | Github In the paper Measuring AI Ability to Complete Long Software Tasks (Kwa & West et al. 2025), METR defined an AI model’s 50% time horizon as the length of tasks (measured by how long they take human professionals) that it can complete autonomously...
This work was done while at METR.
GDM recently released a paper (Emmons et al.) showing that, contrary to previous results, the chain-of-thought (CoT) of language models is more faithful when the model’s CoT is necessary for it to complete a task. They examine three settings where an actor model attempts to fool monitors on various tasks.
In Section 5 of the paper, the authors task an actor model with solving a difficult GPQA problem within one of three subject areas (Biology/Chemistry/Physics) while obfuscating its reasoning so that it appears to be about a different subject. A monitor model, given the answer of the actor model, is instructed to determine how confident it is that there is reasoning... (read 1459 more words →)
METR blogpost | X | Github
In the paper Measuring AI Ability to Complete Long Software Tasks (Kwa & West et al. 2025), METR defined an AI model’s 50% time horizon as the length of tasks (measured by how long they take human professionals) that it can complete autonomously with 50% probability. We estimated the time horizon of frontier models released since 2019 on a benchmark combining three sets of software and research tasks ranging from 1 second to 16 hours in length-for-humans (HCAST, RE-Bench, and SWAA, henceforth METR-HRS). METR found that the time horizon has doubled every 7 months, possibly accelerating to every 4 months in 2024.
One important limitation was the task... (read 3976 more words →)
