All
5+
10+
25+
50+
100+
25
Show HN: ART – a new open-source RL framework for training agents (github.com/openpipe)
2 weeks ago |
kcorbitt
| github.com
|
best
6
ART·E: how we built an email research agent that beats o3 (openpipe.ai)
2 weeks ago |
kcorbitt
| openpipe.ai
|
frontpage
55
Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” (openpipe.ai)
2 months ago |
kcorbitt
| openpipe.ai
|
best
3
Analyzing OpenAI's Reinforcement Fine-Tuning: Less Data, Better Results (openpipe.ai)
5 months ago |
kcorbitt
| openpipe.ai
|
newest
78
Using reinforcement learning and $4.80 of GPU time to find the best HN post (openpipe.ai)
7 months ago |
kcorbitt
| openpipe.ai
|
best
216
Show HN: Agent.exe, a cross-platform app to let 3.5 Sonnet control your machine (github.com/corbt)
7 months ago |
kcorbitt
| github.com
|
best
1
DPO fine-tuning outperforms SFT (openpipe.ai)
7 months ago |
kcorbitt
| openpipe.ai
|
newest
2
OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost (openpipe.ai)
11 months ago |
kcorbitt
| openpipe.ai
|
frontpage
3
What we've learned in 3 days of Llama 3 (openpipe.ai)
a year ago |
kcorbitt
| openpipe.ai
|
newest
1
Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning (openpipe.ai)
a year ago |
kcorbitt
| openpipe.ai
|
newest
1
S-LoRA: Serving Thousands of Models from One GPU for Fun and Profit (openpipe.ai)
a year ago |
kcorbitt
| openpipe.ai
|
newest
174
Is AI the next crypto? Insights from HN comments (openpipe.ai)
a year ago |
kcorbitt
| openpipe.ai
|
best
240
Fine-tune your own Llama 2 to replace GPT-3.5/4
a year ago |
kcorbitt
| ycombinator.com
|
best
2
Show HN: Automatically convert your GPT-3.5 prompt to Llama 2
a year ago |
kcorbitt
| ycombinator.com
|
frontpage
93
TaxyAI: Open-source browser automation with GPT-4 (github.com/taxyai)
2 years ago |
kcorbitt
| github.com
|
best