Seth Karten

sethkarten.ai

12 July 2026 02:42

New blog applying Continual Harness to ARC-AGI-3. The heavy test-time learning required by the benchmark pushes agents to form an internal world model of the rules and mechanics that updates with new evidence. Continual Harness scored 20.54%. sethkarten.substack.com/p/continual-...

Nathan Lambert

natolambert.bsky.social

22 June 2026 18:48

Excited to share a new open-source, RL recipe paper! TMax is the best openly available terminal-bench style training data, establishing the open frontier of small terminal agents with RL training. Many great insights into training in the work led by Hamish Ivison and Oscar Yin.

Kat Abughazaleh

katmabu.bsky.social

05 November 2025 09:37

Good things are possible and we don’t have to settle.

Natasha Jaques

natashajaques.bsky.social

04 October 2025 09:51

Instead of behavior cloning, what if you asked an LLM to write code to describe how an agent was acting, and used this to predict their future behavior? Our new paper "Modeling Others' Minds as Code" shows this outperforms BC by 2x, and reaches human-level performance in predicting human behavior.

Shahab Bakhtiari

shahabbakht.bsky.social

04 October 2025 09:49

The way Sutton himself interprets the “bitter lesson” in this interview definitely caught a lot of bitter lesson enthusiasts off guard. LLMs not actually being an example of the bitter lesson was quite a nuance no one saw coming. youtu.be/21EYKqUsPfg?...