Don't Train the Model, Evolve the Harness
🌿
53
Evolving an agent's harness, not its model, on Harvey's LAB
Sayan Chakraborty
shockroborty
AI & ML interests
LLM, weak supervision, self-supervision
Recent Activity
liked a Space 9 days ago
joelniklaus/harness-optimization liked a model 4 months ago
CohereLabs/cohere-transcribe-03-2026 liked a dataset 4 months ago
nvidia/Nemotron-Personas-USAOrganizations
liked a
Space 9 days ago
liked a
model 4 months ago
liked a
dataset 4 months ago
upvoted a paper 5 months ago
liked a
model 5 months ago
updated a
model 8 months ago
liked a
Space 8 months ago
published a
model 9 months ago
updated a
dataset 9 months ago
published a
dataset 9 months ago
Adding Evaluation Results
#10 opened 10 months ago
by shockroborty
upvoted a collection 10 months ago
liked a
model 10 months ago
updated a
dataset 10 months ago
published a
dataset 10 months ago
updated a
dataset 11 months ago
published a
dataset 11 months ago
liked a
model 11 months ago
upvoted an article 11 months ago
Article
SmolLM3: smol, multilingual, long-context reasoner
- +21
eliebak, cmpatino, anton-l, edbeeching, m-ric, nouamanetazi, akseljoonas, guipenedo, hynky, clefourrier, SaylorTwift, kashif, qgallouedec, hlarcher, glutamatt, Xenova, reach-vb, ngxson, craffel, lewtun, loubnabnl, lvwerra, thomwolf
• • 782 liked a
model about 1 year ago
