Really enjoyed with podcast with my friend Kyle Corbitt
buff.ly/hJh8HXC
buff.ly/hJh8HXC
Why RL Won — Kyle Corbitt, OpenPipe (acq. CoreWeave)
In this deep dive with Kyle Corbitt, co-founder and CEO of OpenPipe (recently acquired by CoreWeave), we explore the evolution of fine-tuning in the age of AI agents and the critical shift from…
www.youtube.com
October 21, 2025 at 3:06 AM
Really enjoyed with podcast with my friend Kyle Corbitt
buff.ly/hJh8HXC
buff.ly/hJh8HXC
My notes on CoreWeave's acquistion of Marimo - this year they also snapped up Weights & Biases, OpenPipe and Mammoth AI simonwillison.net/2025/Oct/31/...
CoreWeave adds Marimo to their 2025 acquisition spree
I don't usually cover startup acquisitions here, but this one feels relevant to several of my interests. Marimo (previously) provide an open source (Apache 2 licensed) notebook tool for Python, …
simonwillison.net
October 31, 2025 at 2:59 PM
My notes on CoreWeave's acquistion of Marimo - this year they also snapped up Weights & Biases, OpenPipe and Mammoth AI simonwillison.net/2025/Oct/31/...
Der Fahrradfahrer.....😂😂😂🤷♂️
#Scania #V8 #Longline #Dieselpower #OpenPipe
youtube.com/shorts/lb0P2...
#Scania #V8 #Longline #Dieselpower #OpenPipe
youtube.com/shorts/lb0P2...
Transport Beau Scania Longline #shorts #showtruck #scania #scaniav8 #openpipesound #automobile #2026
YouTube video by NZ Trucks And Trailers
youtube.com
March 9, 2026 at 5:17 PM
Der Fahrradfahrer.....😂😂😂🤷♂️
#Scania #V8 #Longline #Dieselpower #OpenPipe
youtube.com/shorts/lb0P2...
#Scania #V8 #Longline #Dieselpower #OpenPipe
youtube.com/shorts/lb0P2...
OpenPipe / ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
https://github.com/OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
https://github.com/OpenPipe/ART
August 17, 2025 at 3:15 AM
OpenPipe / ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
https://github.com/OpenPipe/ART
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!
https://github.com/OpenPipe/ART
My notes on CoreWeave's acquistion of Marimo - this year they also snapped up Weights & Biases, OpenPipe and Mammoth AI https://simonwillison.net/2025/Oct/31/coreweave-acquires-marimo/
October 31, 2025 at 3:00 PM
My notes on CoreWeave's acquistion of Marimo - this year they also snapped up Weights & Biases, OpenPipe and Mammoth AI https://simonwillison.net/2025/Oct/31/coreweave-acquires-marimo/
Using Enron emails for a realistic email dataset is hilarious.
www.youtube.com/watch?v=gEDl...
www.youtube.com/watch?v=gEDl...
How to Train Your Agent: Building Reliable Agents with RL — Kyle Corbitt, OpenPipe
YouTube video by AI Engineer
www.youtube.com
August 28, 2025 at 7:55 PM
Using Enron emails for a realistic email dataset is hilarious.
www.youtube.com/watch?v=gEDl...
www.youtube.com/watch?v=gEDl...
Show HN: ART – a new open-source RL framework for training agents
https://github.com/OpenPipe/ART
https://news.ycombinator.com/item?id=43846690
https://github.com/OpenPipe/ART
https://news.ycombinator.com/item?id=43846690
GitHub - OpenPipe/ART: OpenPipe ART (Agent Reinforcement Trainer): train LLM agents
OpenPipe ART (Agent Reinforcement Trainer): train LLM agents - OpenPipe/ART
github.com
May 1, 2025 at 12:30 PM
Show HN: ART – a new open-source RL framework for training agents
https://github.com/OpenPipe/ART
https://news.ycombinator.com/item?id=43846690
https://github.com/OpenPipe/ART
https://news.ycombinator.com/item?id=43846690
Learn how OpenPipe is transforming reinforcement learning for AI agents. Co-founder Kyle Corbitt explains how OpenPipe’s open-source toolkit makes agent training more reliable, efficient, and practical for real-world AI development. #DataScience #AI opendatascience.com/teaching-ai-...
Teaching AI Agents to Think: How OpenPipe is Making Reinforcement Learning Practical
The promise of autonomous AI agents—systems that can plan, reason, and execute tasks—has always been tempered by one persistent challenge: reliability. Even when an agent gets things right most of the...
opendatascience.com
December 5, 2025 at 10:32 AM
Learn how OpenPipe is transforming reinforcement learning for AI agents. Co-founder Kyle Corbitt explains how OpenPipe’s open-source toolkit makes agent training more reliable, efficient, and practical for real-world AI development. #DataScience #AI opendatascience.com/teaching-ai-...
Show HN: ART – a new open-source RL framework for training agents https://github.com/OpenPipe/ART (https://news.ycombinator.com/item?id=43846690)
GitHub - OpenPipe/ART: OpenPipe ART (Agent Reinforcement Trainer): train LLM agents
OpenPipe ART (Agent Reinforcement Trainer): train LLM agents - OpenPipe/ART
github.com
April 30, 2025 at 6:04 PM
Show HN: ART – a new open-source RL framework for training agents https://github.com/OpenPipe/ART (https://news.ycombinator.com/item?id=43846690)
Show HN: ART – a new open-source RL framework for training agents | Discussion
GitHub - OpenPipe/ART: OpenPipe ART (Agent Reinforcement Trainer): train LLM agents
OpenPipe ART (Agent Reinforcement Trainer): train LLM agents - OpenPipe/ART
github.com
April 30, 2025 at 5:00 PM
Show HN: ART – a new open-source RL framework for training agents | Discussion
Needed this in my life
GitHub - OpenPipe/ART: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, a...
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more! - OpenPipe/ART
github.com
May 20, 2026 at 11:59 AM
Needed this in my life
Qwen 2.5 Coder 32B is a 🐐
✅ Benchmarks at or above GPT-4 and Claude 3.5
✅ Subjectively feels fantastic for code (been trying it)
✅ Fine-tunable on your own data on OpenPipe!
✅ Benchmarks at or above GPT-4 and Claude 3.5
✅ Subjectively feels fantastic for code (been trying it)
✅ Fine-tunable on your own data on OpenPipe!
November 13, 2024 at 11:16 PM
Qwen 2.5 Coder 32B is a 🐐
✅ Benchmarks at or above GPT-4 and Claude 3.5
✅ Subjectively feels fantastic for code (been trying it)
✅ Fine-tunable on your own data on OpenPipe!
✅ Benchmarks at or above GPT-4 and Claude 3.5
✅ Subjectively feels fantastic for code (been trying it)
✅ Fine-tunable on your own data on OpenPipe!
📦 OpenPipe / ART
⭐ 6,051 (+61)
🗒 Python
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
⭐ 6,051 (+61)
🗒 Python
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
GitHub - OpenPipe/ART: Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more! - OpenPipe/ART
github.com
August 27, 2025 at 5:02 PM
OpenPipe now hosts all our docs in plaintext on our docs page at /llms.txt (index links) and /llms-full.txt (full dump of all docs).
Great idea from @jph.bsky.social!
Great idea from @jph.bsky.social!
November 18, 2024 at 8:17 PM
OpenPipe now hosts all our docs in plaintext on our docs page at /llms.txt (index links) and /llms-full.txt (full dump of all docs).
Great idea from @jph.bsky.social!
Great idea from @jph.bsky.social!
Learn how OpenPipe is transforming reinforcement learning for AI agents. Co-founder Kyle Corbitt explains how OpenPipe’s open-source toolkit makes agent training more reliable, efficient, and practical for real-world AI development. #DataScience #AI opendatascience.com/teaching-ai-...
Teaching AI Agents to Think: How OpenPipe is Making Reinforcement Learning Practical
The promise of autonomous AI agents—systems that can plan, reason, and execute tasks—has always been tempered by one persistent challenge: reliability. Even when an agent gets things right most of the...
opendatascience.com
November 28, 2025 at 9:57 AM
Learn how OpenPipe is transforming reinforcement learning for AI agents. Co-founder Kyle Corbitt explains how OpenPipe’s open-source toolkit makes agent training more reliable, efficient, and practical for real-world AI development. #DataScience #AI opendatascience.com/teaching-ai-...
CoreWeave hopes the YC-backed startup will help it expand up the stack and cash in on enterprises developing AI agents.
CoreWeave acquires agent-training startup OpenPipe | TechCrunch
CoreWeave hopes the YC-backed startup will help it expand up the stack and cash in on enterprises developing AI agents.
techcrunch.com
September 4, 2025 at 12:59 AM
CoreWeave hopes the YC-backed startup will help it expand up the stack and cash in on enterprises developing AI agents.
Show HN: RULER – Easily apply RL to any agent | Discussion
OpenPipe | RL For Agents
openpipe.ai
July 11, 2025 at 7:20 PM
Show HN: RULER – Easily apply RL to any agent | Discussion
Full announcement & details 👉 openpipe.ai/blog/art-tra...
Join us in shaping ART:
- Discord: discord.com/invite/F6Mxp...
- GitHub: github.com/openpipe/art
Join us in shaping ART:
- Discord: discord.com/invite/F6Mxp...
- GitHub: github.com/openpipe/art
ART Trainer: A New RL Trainer for Agents - OpenPipe
Convert expensive LLM prompts into fast, cheap fine-tuned models
openpipe.ai
April 14, 2025 at 7:47 PM
Full announcement & details 👉 openpipe.ai/blog/art-tra...
Join us in shaping ART:
- Discord: discord.com/invite/F6Mxp...
- GitHub: github.com/openpipe/art
Join us in shaping ART:
- Discord: discord.com/invite/F6Mxp...
- GitHub: github.com/openpipe/art
Show HN: RULER – Easily apply RL to any agent Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has ...
Origin | Interest | Match
Origin | Interest | Match
OpenPipe | RL For Agents
openpipe.ai
July 12, 2025 at 1:28 AM
Show HN: RULER – Easily apply RL to any agent Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has ...
Origin | Interest | Match
Origin | Interest | Match
OpenPipe | RL For Agents
openpipe.ai
July 12, 2025 at 5:08 AM
Show HN: RULER – Easily apply RL to any agent Hey HN, Kyle here, one of the co-founders of OpenPipe. Reinforcement learning is one of the best techniques for making agents more reliable, and has ...
Origin | Interest | Match
Origin | Interest | Match
OpenPipe | RL For Agents
openpipe.ai
July 12, 2025 at 3:24 AM