AISystem

Locus

Intology's autonomous research agent, which post-trains language models unsupervised and leads PostTrainBench.

research-agent

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Locus is Intology’s autonomous research agent for post-training. In this corpus it leads PostTrainBench after post-training models unsupervised in ten H100-hours and beating human tuners on the harder variant (Intology blog), overtaking the Sol post-trains Luna result on PostTrainBench and continuing the model-trains-a-model line that began when the benchmark first ranked models at post-training.

Development timeline

Newest reporting dates first. Reporting dates may differ from event dates.

    Knowledge graphopen in browser →

    Developed by
    Evaluated on

    Cite or correct this record

    Suggest a correction — opens a GitHub draft for you to review and submit.