Home / Companies / OpenPipe / Hacker News

OpenPipe on HN

20 posts with 1+ points since 2023

Filters
Since:
Posts by Month (20 total)
Hacker News Posts
Title Points Comments Date
Is AI the next crypto? Insights from HN comments 237 -- 2023-11-08
Mistral 7B Fine-Tune Optimized 234 -- 2023-12-20
Using reinforcement learning and $4.80 of GPU time to find the best … 217 -- 2024-10-28
Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” 199 -- 2025-03-06
Show HN: RULER – Easily apply RL to any agent 81 -- 2025-07-11
OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost 13 -- 2024-06-20
Serverless RL: Faster, Cheaper and More Flexible RL Training 9 -- 2025-10-08
PII-Redact – SOTA PII Redaction on Your Laptop 6 -- 2025-03-26
Analyzing OpenAI's Reinforcement Fine-Tuning: Less Data, Better Results 4 -- 2024-12-30
Fine-Tuning Best Practices Series Introduction and Chapter 1: Training Data 3 -- 2024-08-29
What we've learned in 3 days of Llama 3 3 -- 2024-04-22
ART·E: how we built an email research agent that beats o3 3 -- 2025-04-29
Everything I know about reward hacking 3 -- 2025-06-12
LLM Fine-Tuning Best Practices: Base Models Proprietary/Open Source, Large/Small 2 -- 2024-08-28
Fine-Tuning for Production Apps 2 -- 2024-09-02
Open Deep Research Tutorial – Train a deep research agent to exceed … 2 -- 2025-09-02
DPO fine-tuning outperforms SFT 1 -- 2024-10-02
Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning 1 -- 2024-02-29
S-LoRA: Serving Thousands of Models from One GPU for Fun and Profit 1 -- 2024-01-18
Summary-RL 1 -- 2025-06-26
Plushcap, by Matt Makai. 2021-2026.