HNHacker News
TopNewBestAskShowJobs

codelion

3,064 karma · joined February 23, 2008

submissionscomments

Neural Drive

mlx-optiq.com·2 pts·codelion·
0

Cross-Lingual Alignment Without Joint Training

arxiv.org·1 pts·codelion·
0

Voice AI Benchmarks: a directory of voice-agent evaluations

voicebenchmarks.com·2 pts·codelion·
0

Neural Canvas: a fruit fly connectome demo in the browser

huggingface.co·2 pts·codelion·
0

Iris: Climbing to the Search Frontier

arxiv.org·1 pts·codelion·
0

The Recursive Economy: AI Self-Improvement and Scarcity

recursive-economy.pages.dev·2 pts·codelion·
0

Neural Drive, a SuperTuxKart World Model that runs in the browser

huggingface.co·2 pts·codelion·
0

Coding agent for local models on a Mac

mlx-optiq.com·1 pts·codelion·
0

Frame: Grounding LLM Vulnerability Detection with a Sound Separation-Logic Core

lambdasec.github.io·2 pts·codelion·
0

Mlx-optiq: per-layer mixed-precision LLM quantization for Apple Silicon

mlx-optiq.com·2 pts·codelion·
0

A 1B humanizer that matches human writing on an AI detector

mlx-optiq.com·3 pts·codelion·
0

Zero-Dependency Programming

conjure.pages.dev·2 pts·codelion·
0

Scaling Pedagogical Pre-Training: From Optimal Mixing to 10B Tokens

huggingface.co·2 pts·codelion·
0

From HashHop to Memory-Augmented Language Models

huggingface.co·2 pts·codelion·
0

The Optimal Architecture for Small Language Models

huggingface.co·1 pts·codelion·
0

Enhancing LLMs with LoRA – Standardized Recipes for Capability Enhancement

huggingface.co·3 pts·codelion·
0

OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution

algorithmicsuperintelligence.ai·53 pts·codelion·
9

Ellora: Enhancing LLMs with LoRA Standardized Recipes for Capability Enhancement

huggingface.co·1 pts·codelion·
0

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

huggingface.co·6 pts·codelion·
0

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

huggingface.co·3 pts·codelion·
0

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

huggingface.co·2 pts·codelion·
1

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

github.com·1 pts·codelion·
0

Unsupervised Model Improvement via Internal Coherence Maximization

huggingface.co·1 pts·codelion·
0

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

2 pts·codelion·
0

Automated Discovery of High-Performance GPU Kernels with OpenEvolve

huggingface.co·4 pts·codelion·
0

Adaptive Classifier: Dynamic Text Classification with Continuous Learning

huggingface.co·1 pts·codelion·
0

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

4 pts·codelion·
0

Eliciting Fine-Tuned Transformer Capabilities via Inference-Time Techniques

arxiv.org·1 pts·codelion·
0

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

48 pts·codelion·
13

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

397 pts·codelion·
68
Page 1 of 9Next →