Evidence item

Pachocki's OpenAI essay says RLSlow produced the first results giving confidence that reasoning-model training could scale. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10713

Source: An Alien Mind · locator {} · excerpt hash sha256:bd55a70a073403f326c649c057a3a5726f631c8d0086a4ffd90645558cfbe6cf

In mid-2023, within the “RLSlow” research project, we saw the first results that gave us confidence that we will be able to scale the training of reasoning models, unlocking the capability of pretrained models to form their own chains of thought.