Article
One sandbox per rollout, or how labs run RL for agents in 2026
sergiopaniego
• • 10Sergio Paniego PRO
sergiopaniego
AI & ML interests
None yet
Recent Activity
updated a dataset about 3 hours ago
agents-course/final-certificates updated a dataset about 3 hours ago
agents-course/course-certificates-of-excellence updated a dataset about 5 hours ago
huggingface-projects/Deep-RL-Course-CertificationOrganizations
published an article 16 days ago
published an article 17 days ago
Article
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
- +2
aminediroHF, qgallouedec, kashif, sergiopaniego
• • 53 published an article 20 days ago
Article
Why RL environments work now (and could not in 2016)
sergiopaniego
• • 1 published an article 24 days ago
Article
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
- +1
iamleonie, burtenshaw, sergiopaniego
• • 138 published an article 24 days ago
Article
Training a coding model to paint watercolours with TRL and OpenEnv
sergiopaniego
• • 73 published an article about 2 months ago
Article
How frontier models train on outcomes in 2026
sergiopaniego
• • 8 published an article about 2 months ago
Article
Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv
sergiopaniego
• • 29 published an article about 2 months ago
Article
Can you train a model on Simon Willison's deeply unscientific pelican benchmark?
sergiopaniego
• • 2 published an article 3 months ago
Article
Profiling in PyTorch (Part 3): Attention is all you profile
- +2
ariG23498, sergiopaniego, sayakpaul, ror
• • 50 published an article 3 months ago
Article
Distillation in 2026 (so far): which frontier models use it and how
sergiopaniego
• • 22 published an article 3 months ago
Article
A brief history of distillation in AI
sergiopaniego
• • 4 published an article 3 months ago
Article
Continuous batching for GRPO, now in TRL
sergiopaniego
• • 8 published an article 3 months ago
Article
I fine-tuned a model for free from one prompt, with TRL and the Google Colab CLI
sergiopaniego
• • 8 published an article 4 months ago
Article
Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP
- +3
ariG23498, ror, sergiopaniego, pcuenq, sayakpaul
• • 63 published an article 4 months ago
Article
The Open Source Community is backing OpenEnv for Agentic RL
- +18
burtenshaw, spisakjo, lysandre, darktex, willcb, qjoy, pawalt, cwing-nv, danielhanchen, andrewzhou, thegovind, shimmyshimmer, Hamid-Nazeri, Sanyam, zkwentz, emre0, lewtun, sergiopaniego, banghua, unseenmars
• • 118 published an article 4 months ago
Article
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler
- +3
ariG23498, sayakpaul, sergiopaniego, ror, pcuenq
• • 168 published an article 4 months ago
Article
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
- +6
aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, lvwerra, sergiopaniego
• • 50 published an article 4 months ago
Article
Harness, Scaffold, and the AI Agent Terms Worth Getting Right
sergiopaniego, ariG23498
• • 148 published an article 6 months ago
Article
Welcome Gemma 4: Frontier multimodal intelligence on device
- +5
merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift
• • 929 published an article 6 months ago
Article
TRL v1.0: Post-Training Library Built to Move with the Field
- +2
qgallouedec, stevhliu, pcuenq, sergiopaniego
• • 60