Post-training

…and customization through post-training or optimization of prompts, tools and agent scaffolding. Research may address safe agent behavior, data integration, enterprise operation and human–AI collaboration. Submit a scientific proposal using the ARA template, encouraged to be no more than four pages excluding appendices. Decisions are expected in February 2027. Applications close on 4 November 2026 at 11:59pm Pacific Time.

Nathan Lambert discusses post-training and the prospects for open AI models, drawing on his work on OLMo at Ai2 and his writing on reinforcement learning from human feedback. Topics include capability gaps, the economics of the open ecosystem, training environments, continual learning and skepticism about recursive self-improvement. The conversation also examines research culture, concentrated talent and whether increased model spending translates into better products. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

…examines training, serving and post-training challenges, controllable generation and possible directions for multimodal diffusion systems.