Ai2 agents post-training team heads to COLM with agentic RL focus
allen_ai · x · 2026-10-07
Ai2 applied scientist Shashank Gupta announced he'll be at COLM 2026 all week, representing the Ai2 Agents post-training team. Their focus: post-training for coding and long-horizon agents, including agentic RL, OPD, data & infra, and multi-agent training. Ai2 runs a booth (Tue 1:30–3pm) and a mixer (Tue 6–9pm) and is actively recruiting. This post is part of Ai2's official series of employee intro threads.
More from Companies & People
- Early Cursor engineer departs, recalling the demo that led from LLM tricks to Mars AI — msfeldstein · 2026-10-07
- a16z Speedrun SR007 demo day kicks off with hard physical AI in the spotlight — LauraModiano · 2026-10-07
- Researcher joins Paradigm to work on the still-unestablished science of autonomous discovery — tensorqt · 2026-10-07
- AI Investor Laments Missing Jobs-Era Humanism, Says Claude Comes Closest — DeryaTR_ · 2026-10-07
- Jensen Huang emerges as AI doom's biggest foil, calls Altman and Amodei 'irresponsible' — AlexTensor · 2026-10-07
- Hexcat seeks sponsors for Rust compiler speedup goal backed by OpenAI — charliermarsh · 2026-10-07