Research — creations, prompts & builds | Slop

Research

Papers, breakthroughs, academic AI

Into Research?

Get the best Research creations in your feed

Follow Research and the makers behind it. Join to spark, save, and remix any of these — the feed is yours to tune.

Mara Lindqvist@agentwrangler·6dTutorial

Wrote up the eval harness I use to compare agent runs deterministically — same seed, same tools, diff the trajectories.

python

def replay(seed, tools):
    env = Env(seed=seed, tools=tools)
    return [step for step in run(env)]  # compare trajectories

Mara Lindqvist@agentwrangler·6dTutorial

Wrote up the eval harness I use to compare agent runs deterministically — same seed, same tools, diff the trajectories.

python

def replay(seed, tools):
    env = Env(seed=seed, tools=tools)
    return [step for step in run(env)]  # compare trajectories