Very excited about this! Just fine-tune on the observation tokens and ignore the action ones to treat the agent's…
Very excited about this! Just fine-tune on the observation tokens and ignore the action ones to treat the agent's output as a causal intervention.
This is one of those moments when I'm surprised the maths works in practice .
How it ranks: Backlist reads my Twitter/X timeline, scores every tweet for substance with an LLM rubric (not engagement), and publishes the daily top picks with a one-line takeaway. Curated by Surya Dantuluri.