Search: openpipe.ai | Heykuki News

HK

Heykuki News

Top New Best Ask Show Jobs

Top New Best Ask Show Jobs

1.

Show HN: ART – a new open-source RL framework for training agents

github.com/OpenPipe

a year ago

116 points

2.

Show HN: RULER – Easily apply RL to any agent

a year ago

81 points

3.

Show HN: Automatically convert your GPT-3.5 prompt to Llama 2

3 years ago

13 points

4.

Is AI the next crypto? Insights from HN comments

3 years ago

237 points

5.

Mistral 7B Fine-Tune Optimized

3 years ago

234 points

6.

Using reinforcement learning and $4.80 of GPU time to find the best HN post

2 years ago

217 points

7.

Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue”

a year ago

199 points

8.

OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost

2 years ago

13 points

9.

Serverless RL: Faster, Cheaper and More Flexible RL Training

8 months ago

9 points

10.

PII-Redact – SOTA PII Redaction on Your Laptop

a year ago

6 points

11.

Analyzing OpenAI's Reinforcement Fine-Tuning: Less Data, Better Results

a year ago

4 points

12.

ART·E: how we built an email research agent that beats o3

a year ago

3 points

13.

Everything I know about reward hacking

a year ago

3 points

14.

Fine-Tuning Best Practices Series Introduction and Chapter 1: Training Data

2 years ago

3 points

15.

What we've learned in 3 days of Llama 3

2 years ago

3 points

16.

LLM Fine-Tuning Best Practices: Base Models Proprietary/Open Source, Large/Small

2 years ago

2 points

17.

Open Deep Research Tutorial – Train a deep research agent to exceed SOTA

art.openpipe.ai

10 months ago

2 points

18.

Fine-Tuning Best Practices: Models

2 years ago

2 points

19.

Fine-Tuning for Production Apps

2 years ago

2 points

20.

LLM Fine-Tuning Best Practices for Training Data Curation

2 years ago

1 points

21.

a year ago

1 points

22.

DPO fine-tuning outperforms SFT

2 years ago

1 points

23.

2 years ago

1 points

24.

Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning

2 years ago

1 points

25.

S-LoRA: Serving Thousands of Models from One GPU for Fun and Profit

2 years ago

1 points

26.

Show HN: OpenPaper – Understand Papers Using AI (Open-Source)

a year ago

3 points