underscore2/modernbert_large_slop_writing
Text Classification
•
0.4B
•
Updated
•
2
Underscore
underscore2
AI & ML interests
cooming
Recent Activity
updated
a model
about 19 hours ago
underscore2/modernbert_large_slop_writing
published
a model
about 19 hours ago
underscore2/modernbert_large_slop_writing
Organizations
None yet
updated
a
model
about 19 hours ago
published
a
model
about 19 hours ago
reacted to
codelion's
post with 🔥
about 20 hours ago
Post
3477
🧬 We just published our comprehensive analysis of OpenEvolve - an open-source evolutionary coding agent that automatically optimizes algorithms using LLMs!
Our key findings from 29 experiments across 10 models:
- Gemini Flash 2.5 achieved 2.04x speedup across 30 benchmark tasks
- Open models like Gemma 3 27B (1.63x) and Qwen3-Coder 480B (1.41x) rivaled proprietary models
- The system discovered entirely new algorithms - not just code optimizations!
- One task evolved from DFS to BFS to Union-Find approaches
- Specialized coding models outperformed much larger general models 200 iterations beat 100 iterations by 24%
- Ensembles surprisingly failed due to conflicting optimization strategies
Most fascinating: watching models evolve code step-by-step, like transforming matrix operations from basic eigendecomposition to vectorized one-liners with 32x speedup.
Our systematic experimental approach reveals that open-source evolutionary coding is becoming seriously competitive with proprietary solutions. We tested everything from temperature settings to evolution strategies to find optimal configurations.
This research shows automated code optimization is ready for real-world applications. The methodology we developed can guide anyone building evolutionary coding systems.
Full paper with code examples, detailed methodology, and all experimental results: https://huggingface.co/blog/driaforall/towards-open-evolutionary-agents
What optimization challenges could benefit from evolutionary approaches in your work?
Our key findings from 29 experiments across 10 models:
- Gemini Flash 2.5 achieved 2.04x speedup across 30 benchmark tasks
- Open models like Gemma 3 27B (1.63x) and Qwen3-Coder 480B (1.41x) rivaled proprietary models
- The system discovered entirely new algorithms - not just code optimizations!
- One task evolved from DFS to BFS to Union-Find approaches
- Specialized coding models outperformed much larger general models 200 iterations beat 100 iterations by 24%
- Ensembles surprisingly failed due to conflicting optimization strategies
Most fascinating: watching models evolve code step-by-step, like transforming matrix operations from basic eigendecomposition to vectorized one-liners with 32x speedup.
Our systematic experimental approach reveals that open-source evolutionary coding is becoming seriously competitive with proprietary solutions. We tested everything from temperature settings to evolution strategies to find optimal configurations.
This research shows automated code optimization is ready for real-world applications. The methodology we developed can guide anyone building evolutionary coding systems.
Full paper with code examples, detailed methodology, and all experimental results: https://huggingface.co/blog/driaforall/towards-open-evolutionary-agents
What optimization challenges could benefit from evolutionary approaches in your work?
updated
a
model
1 day ago
published
a
model
1 day ago
liked
a
model
8 days ago
updated
a
model
11 days ago
published
a
model
11 days ago
updated
a
model
12 days ago
published
a
model
12 days ago
updated
a
model
13 days ago
published
a
model
13 days ago
updated
a
dataset
13 days ago
published
a
dataset
13 days ago
updated
a
model
14 days ago
Discussion about ethics/risks
34
#1 opened 24 days ago
by
owao
liked
a
model
22 days ago
published
a
model
23 days ago
liked
a
model
24 days ago
🚨REPORT: Trent M Kelly Is a commie????
1
#1 opened 24 days ago
by
underscore2