Don't Train the Model, Evolve the Harness
🌿
69
Evolving an agent's harness, not its model, on Harvey's LAB
Josh Ause
joshause
AI & ML interests
None yet
Recent Activity
liked a Space 3 months ago
joelniklaus/harness-optimization liked a model 3 months ago
Harahan/QVGen-CogVideoX-2B-W4A4 liked a Space 4 months ago
justforkicks/sae-gpu-backendOrganizations
None yet
liked a
Space 3 months ago
liked a
model 3 months ago
liked a
Space 4 months ago
liked 2
models 4 months ago
liked 6
Spaces 4 months ago
Gemma 3 12b It
🔥
165
Chat with an AI that understands text, images, and videos
Gemma 4 12B IT
⚡
155
Chat with an AI using text, images, audio, or video
PROMETHEUS v1.0 — World Model Interactive Demo
🔥
58
World-first embodied AI world model
WORLD MODEL Leaderboard
💻
26
WORLD MODEL Bench
DVD-JEPA
📺
2
A browser JEPA world model of a bouncing DVD logo
Wan2.2 14B Slow Preview
🐌
2.18k
generate a video from an image with a text prompt
upvoted a paper 4 months ago
liked a
model 4 months ago
liked a
Space 4 months ago
liked a
model 4 months ago
upvoted 3
papers 4 months ago
LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Paper • 2603.19312 • Published • 56
Causal-JEPA: Learning World Models through Object-Level Latent Interventions
Paper • 2602.11389 • Published • 13
ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model
Paper • 2603.22281 • Published • 22
liked a
Space 4 months ago
upvoted a paper 4 months ago