Stories by codelion

OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution

Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement

The 1B Token Challenge: Finding the Perfect Pre-Training Mix

The 1B Token Challenge: Finding the Perfect Pre-Training Mix

Pivotal Token Search (PTS): Targeting Critical Decision Points in LLM Training

Internal Coherence Maximization(ICM): Label-Free Unsupervised Training Framework

Unsupervised Model Improvement via Internal Coherence Maximization

Show HN: PTS Library – Analyze LLM reasoning through "thought anchors"

Automated Discovery of High-Performance GPU Kernels with OpenEvolve

Adaptive Classifier: Dynamic Text Classification with Continuous Learning

Show HN: DeepThink Plugin – Bring Gemini 2.5's parallel reasoning to open models

Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques

Show HN: System Prompt Learning – LLMs Learn Problem-Solving from Experience

Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning

Show HN: OpenEvolve – open-source implementation of DeepMind's AlphaEvolve

Pivotal Token Search (PTS): Identify critical decision points in LLM generations

Show HN: An adaptive classifier that detects hallucinations in LLM/RAG outputs

Show HN: OptiLLMBench – Test how inference optimization tricks scale up LLMs

Adaptive Classification for Automatic LLM Temperature Optimization

Show HN: A classifier that learns new categories without retraining from scratch

1
2
3
4
5
6
7
8
9
10